Person Action Recognition/Detection

Size: px
Start display at page:

Download "Person Action Recognition/Detection"

Transcription

1 Person Action Recognition/Detection Fabrício Ceschin Visão Computacional Prof. David Menotti Departamento de Informática - Universidade Federal do Paraná 1

2 In object recognition: is there a chair in the image? In object detection: is there a chair and where is it in the image? 2

3 In action recognition: is there an action present in the video? In action detection: is there an action and where is it in the video? 3

4 4

5 Datasets 5

6 KTH Six types of human actions: walking, jogging, running, boxing, hand waving and hand clapping Four different scenarios: outdoors s1, outdoors with scale variation s2, outdoors with different clothes s3 and indoors s sequences taken with a static camera with 25 fps. 6

7 Hollywood2 12 classes of human actions. 10 classes of scenes distributed over 3669 video clips from 69 movies. Approximately 20.1 hours of video in total. 7

8 UCF Sports Action Data Set Set of actions collected from various sports which are typically featured on broadcast television channels such as the BBC and ESPN. 10 classes of human actions. 150 sequences with the resolution of 720 x

9 UCF YouTube Action Data Set 11 action categories collected from YouTube and personal videos. Challenging due to large variations in camera motion, object pose and appearance, object scale, viewpoint, cluttered background, illumination conditions, etc. 9

10 JHMDB 51 categories, 928 clips, frames. Puppet flow per frame (approximated optical flow on the person). Puppet mask per frame. Joint positions per frame. Action label per clip. Meta label per clip (camera motion, visible body parts, camera viewpoint, number of people, video quality). 10

11 Articles 11

12 Timeline Learning realistic human actions from movies Ivan Laptev, Marcin Marszałek, Cordelia Schmid and Cordelia Schmid CVPR Dense Trajectories and Motion Boundary Descriptors for Action Recognition Heng Wang, Alexander Kl aser, Cordelia Schmid and Cheng-Lin Liu IJCV Two-Stream Convolutional Networks for Action Recognition in Videos Finding Action Tubes Georgia Gkioxari Jitendra Malik CVPR 2015 Karen Simonyan Andrew Zisserman NIPS

13 Learning Realistic Human Actions from Movies Ivan Laptev, Marcin Marszałek, Cordelia Schmid and Cordelia Schmid CVPR 13

14 Introduction & Dataset Generation Inspired by new robust methods for image description and classification. First version of Hollywood dataset. Movies contain a rich variety and a large number of realistic human actions. To avoid the difficulty of manual annotation, the dataset was build using script-based action annotation. Time information is transferred from subtitles to scripts and then time intervals for scene descriptions are inferred - 60% precision achieved. Learning Realistic Human Actions from Movies 14

15 Script-based Action Annotation Example of matching speech sections (green) in subtitles and scripts. Time information (blue) from adjacent speech sections is used to estimate time intervals of scene descriptions (yellow). Learning Realistic Human Actions from Movies 15

16 Space-time Features Detect interest points using a space-time extension of the Harris operator. Histogram descriptors of space-time volumes are computed in the neighborhood of detected points (the size of each volume is related to the detection scales). Each volume is subdivided into a (Nx, Ny, Nt) grid of cuboids; for each cuboid HOG and HOF are computed. Both are concatenated, creating a descriptor vector. Learning Realistic Human Actions from Movies 16

17 Space-time Features Space-time interest points detected for two video frames with human actions hand shake (left) and get out car (right). Result of detecting the strongest spatio-temporal interest points in a football sequence with a player heading the ball (a) and in a hand clapping sequence (b). Learning Realistic Human Actions from Movies 17

18 Spatio-temporal Bag-of-features A visual vocabulary is built clustering a subset of 100k features sampled from the training videos with the k-means algorithm, with k=4000. BoF assigns each feature to the closest (Euclidean distance) vocabulary word and computes the histogram of visual word occurrences over a space-time volume corresponding either to the entire video sequence or subsequences defined by a spatio-temporal grid. Learning Realistic Human Actions from Movies 18

19 Spatio-temporal Bag-of-features Bag-of-features illustration. Learning Realistic Human Actions from Movies 19

20 Classification Support Vector Machine (SVM) with a multi-channel X² kernel that combines channels. Defined by: Where Hi={hin} and Hj={Hjn} are the histograms for channel c and Dc(Hi,Hj) is the X² distance defined as: Learning Realistic Human Actions from Movies 20

21 Results Average class accuracy on the KTH actions dataset: Method Schuldt et al. Niebles et al. Wong et al. This work Accuracy 71.7% 81.5% 86.7% 91.8% Learning Realistic Human Actions from Movies 21

22 Results Average precision (AP) for each action class of test set - results for clean (annotated), automatic training data and for a random classifier (chance) Clean Automatic Chance AnswerPhone 32.1% 16.4% 10.6% GetOutCar 41.5% 16.4% 6.0% HandShake 32.3% 9.9% 8.8% HugPerson 40.6% 26.8% 10.1% Kiss 53.3% 45.1% 23.5% SitDown 38.6% 24.8% 13.8% SitUp 18.2% 10.4% 4.6% StandUp 50.5% 33.6% 22.6% Learning Realistic Human Actions from Movies 22

23 Dense Trajectories and Motion Boundary Descriptors for Action Recognition Heng Wang, Alexander Kl aser, Cordelia Schmid and Cheng-Lin Liu IJCV

24 Introduction Bag-of-features achieves state-of-the-art performance. Feature trajectories have shown to be efficient for representing videos. Generally extracted using KLT tracker or matching SIFT descriptors between frames, however, quantity and quality are not enough. Video description by dense trajectories Dense trajectories and motion boundary descriptors for a.r. 24

25 Dense Trajectories Separate sample feature points on a grid spaced by W pixels (W=5). Sampling is carried out on each spatial scale separately and the goal is to track all these sampled points through the video. Areas without any structure are removed (if the eigenvalues of the auto-correlation matrix are very small - few explanation ). Feature points are tracked on each spatial scale separately. Features are extracted using grids of cuboids, similar to last article Dense trajectories and motion boundary descriptors for a.r. 25

26 Dense Trajectories Left: feature points are densely sampled on a grid for each spatial scale. Middle: tracking is carried out in the corresponding spatial scale for L frames by median filtering in a dense optical flow field. Right: trajectory shape is represented by relative point coordinates. The descriptors (HOG, HOF, MBH) are computed along the trajectory in a N N pixels neighborhood, which is divided into grids of cuboids *Motion boundary histograms (MBH) are extracted by computing derivatives separately for the horizontal and vertical components of the optical flow. Dense trajectories and motion boundary descriptors for a.r. 26

27 Dense Trajectories 2013 Dense trajectories and motion boundary descriptors for a.r. 27

28 Results Comparison of different descriptors and methods for extracting trajectories on nine datasets. Mean average precision is reported over all classes (map) for Hollywood2 and Olympic Sports, average accuracy over all classes for the other seven datasets. The three best results for each dataset are in bold Dense trajectories and motion boundary descriptors for a.r. 28

29 Two-Stream Convolutional Networks for Action Recognition in Videos Karen Simonyan and Andrew Zisserman NIPS

30 Introduction CNNs work very well for image recognition. Extend CNN to action recognition in video. Two separate recognition streams related to the two-stream hypothesis: Spatial Stream - appearance recognition ConvNet. Temporal Stream - motion recognition ConvNet Two-Stream Convolutional Networks for Action Recognition in Videos 30

31 Two-stream Hypothesis Ventral pathway (purple, what pathway ) responds to shape, color and texture. Dorsal pathway (green, where pathway ) responds to spatial transformations and movement Two-Stream Convolutional Networks for Action Recognition in Videos 31

32 Two-stream Architecture for Video Recognition Spatial part: in the form of individual frame appearance, carries information about scenes and objects in the video. Temporal part: in the form of motion across the frames, carries information about the movement of the camera and the objects Two-Stream Convolutional Networks for Action Recognition in Videos 32

33 Two-stream Architecture for Video Recognition Each stream is implemented using a deep ConvNet, softmax scores which are combined by fusion methods. Two fusion methods proposed: Averaging. Training a multiclass linear SVM on stacked L2-normalised softmax scores as features Two-Stream Convolutional Networks for Action Recognition in Videos 33

34 The Spatial Stream ConvNet Similar model used for image classification. Operates on individual video frames. Static appearance is a useful feature, due to actions that are strongly associated with particular objects. Network pre-trained on a large image classification dataset, such as the ImageNet challenge dataset Two-Stream Convolutional Networks for Action Recognition in Videos 34

35 The Temporal Stream ConvNet Input of the ConvNet model is stacking optical flow displacement fields between several consecutive frames. This input describes the motion between video frame. Motion representation: Optical flow stacking: displacement vector fields dtx and dty of L consecutive frames are stacked, creating a total of 2L input channels. Trajectory stacking: trajectory-based descriptors. Bi-directional optical flow, mean flow subtraction Two-Stream Convolutional Networks for Action Recognition in Videos 35

36 Optical Flow Stacking Displacement vector fields dtx and dty of L consecutive frames are stacked, creating a total of 2L input channels. Examples: higher intensity corresponds to positive values, lower intensity to negative values. (a) Horizontal component dx of the displacement vector field (b) Vertical component dy of the displacement vector field. Two-Stream Convolutional Networks for Action Recognition in Videos 36

37 Multi-task Learning Unlike the spatial stream ConvNet, which can be pre-trained on a large still image classification dataset (such as ImageNet), the temporal ConvNet needs to be trained on video data. Available datasets for video action classification are still rather small. UCF-101 and HMDB-51 datasets have only 9.5K and 3.7K, respectively. ConvNet architecture is modified so that it has two softmax classification layers on top of the last fully-connected layer: one softmax layer computes HMDB-51 classification scores, the other one the UCF-101 scores. Each of the layers is equipped with its own loss function, which operates only on the videos, coming from the respective dataset. The overall training loss is computed as the sum of the individual tasks losses Two-Stream Convolutional Networks for Action Recognition in Videos 37

38 Results Two-Stream Convolutional Networks for Action Recognition in Videos 38

39 Finding Action Tubes Georgia Gkioxari and Jitendra Malik CVPR

40 Introduction Image region proposals: regions that are motion salient are more likely to contain the action, so they are selected. Significant reduction in the number of regions being processed and faster computations. Detection pipeline also is inspired by the human vision system. Outperforms other techniques in the task of action detection Finding Action Tubes

41 Regions of Interest Selective search are used on the RGB frames to generate approximately 2K regions per frame. Regions that are void of motion are discarded using the optical flow signal. Motion saliency algorithm: Normalized magnitude of optical flow signal (fm) is seen as a heat map at the pixel level. If R is a region, then fm(r) = 1/( R ) i R fm(i) is a measure of how motion salient R is ɑ. R is discarded if fm(r) < ɑ. For ɑ = 0.3, approximately 85% of boxes are discarded Finding Action Tubes

42 Feature Extraction (a) Candidate regions are fed into action specific classifiers, which make predictions using static and motion cues. (b) The regions are linked across frames based on the action predictions and their spatial overlap. Action tubes are produced for each action and each video Finding Action Tubes

43 Action Detection Model Action specific SVM classifiers are used on spatio-temporal features. The features are extracted from the fc7 layer of two CNNs, spatial-cnn and motion-cnn, which were trained to detect actions using static and motion cues, respectively. The architecture of spatial-cnn and motion-cnn is similar to the ones used for image classification Finding Action Tubes

44 This approach yields an accuracy of 62.5%, averaged over the three splits of JHMDB Finding Action Tubes

45 General Results Dataset Ivan Laptev et al. Heng Wang et al Karen Simonyan et al Georgia Gkioxari et al KTH 91.8% 95.0% - - Hollywood2 38,38%* 58.2% - - UCF Youtube % - - UCF Sports % 88.0% 75.8% JHMDB % 59.4% 62.5% *First version of Hollywood2. 45

46 References Articles Learning Realistic Human Actions from Movies - Ivan Laptev, Marcin Marszałek, Cordelia Schmid, Cordelia Schmid - CVPR Action Recognition with Improved Trajectories - Heng Wang and Cordelia Schmid - CVPR 2013 Dense trajectories and motion boundary descriptors for action recognitionheng Wang, Alexander Kl aser, Cordelia Schmid, Cheng-Lin Liu - IJCV 2013 Two-Stream Convolutional Networks for Action Recognition in Videos Karen Simonyan and Andrew Zisserman - NIPS 2014 Finding Action Tubes - Georgia Gkioxari and Jitendra Malik - CVPR

47 References Datasets KTH Dataset UCF YouTube Action Data Set Hollywood2 Dataset UCF Sports Action Data Set Joint-annotated Human Motion Data Base (JHMDB) 47

Two-Stream Convolutional Networks for Action Recognition in Videos

Two-Stream Convolutional Networks for Action Recognition in Videos Two-Stream Convolutional Networks for Action Recognition in Videos Karen Simonyan Andrew Zisserman Cemil Zalluhoğlu Introduction Aim Extend deep Convolution Networks to action recognition in video. Motivation

More information

Learning realistic human actions from movies

Learning realistic human actions from movies Learning realistic human actions from movies Ivan Laptev, Marcin Marszalek, Cordelia Schmid, Benjamin Rozenfeld CVPR 2008 Presented by Piotr Mirowski Courant Institute, NYU Advanced Vision class, November

More information

Action recognition in videos

Action recognition in videos Action recognition in videos Cordelia Schmid INRIA Grenoble Joint work with V. Ferrari, A. Gaidon, Z. Harchaoui, A. Klaeser, A. Prest, H. Wang Action recognition - goal Short actions, i.e. drinking, sit

More information

Learning Realistic Human Actions from Movies

Learning Realistic Human Actions from Movies Learning Realistic Human Actions from Movies Ivan Laptev*, Marcin Marszałek**, Cordelia Schmid**, Benjamin Rozenfeld*** INRIA Rennes, France ** INRIA Grenoble, France *** Bar-Ilan University, Israel Presented

More information

Deep Learning For Video Classification. Presented by Natalie Carlebach & Gil Sharon

Deep Learning For Video Classification. Presented by Natalie Carlebach & Gil Sharon Deep Learning For Video Classification Presented by Natalie Carlebach & Gil Sharon Overview Of Presentation Motivation Challenges of video classification Common datasets 4 different methods presented in

More information

Lecture 18: Human Motion Recognition

Lecture 18: Human Motion Recognition Lecture 18: Human Motion Recognition Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today? Introduction Motion classification using template matching Motion classification i using spatio

More information

CS231N Section. Video Understanding 6/1/2018

CS231N Section. Video Understanding 6/1/2018 CS231N Section Video Understanding 6/1/2018 Outline Background / Motivation / History Video Datasets Models Pre-deep learning CNN + RNN 3D convolution Two-stream What we ve seen in class so far... Image

More information

Content-based image and video analysis. Event Recognition

Content-based image and video analysis. Event Recognition Content-based image and video analysis Event Recognition 21.06.2010 What is an event? a thing that happens or takes place, Oxford Dictionary Examples: Human gestures Human actions (running, drinking, etc.)

More information

Action Recognition by Dense Trajectories

Action Recognition by Dense Trajectories Action Recognition by Dense Trajectories Heng Wang, Alexander Kläser, Cordelia Schmid, Liu Cheng-Lin To cite this version: Heng Wang, Alexander Kläser, Cordelia Schmid, Liu Cheng-Lin. Action Recognition

More information

SPATIO-TEMPORAL PYRAMIDAL ACCORDION REPRESENTATION FOR HUMAN ACTION RECOGNITION. Manel Sekma, Mahmoud Mejdoub, Chokri Ben Amar

SPATIO-TEMPORAL PYRAMIDAL ACCORDION REPRESENTATION FOR HUMAN ACTION RECOGNITION. Manel Sekma, Mahmoud Mejdoub, Chokri Ben Amar 2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) SPATIO-TEMPORAL PYRAMIDAL ACCORDION REPRESENTATION FOR HUMAN ACTION RECOGNITION Manel Sekma, Mahmoud Mejdoub, Chokri

More information

Activity Recognition in Temporally Untrimmed Videos

Activity Recognition in Temporally Untrimmed Videos Activity Recognition in Temporally Untrimmed Videos Bryan Anenberg Stanford University anenberg@stanford.edu Norman Yu Stanford University normanyu@stanford.edu Abstract We investigate strategies to apply

More information

Evaluation of Local Space-time Descriptors based on Cuboid Detector in Human Action Recognition

Evaluation of Local Space-time Descriptors based on Cuboid Detector in Human Action Recognition International Journal of Innovation and Applied Studies ISSN 2028-9324 Vol. 9 No. 4 Dec. 2014, pp. 1708-1717 2014 Innovative Space of Scientific Research Journals http://www.ijias.issr-journals.org/ Evaluation

More information

P-CNN: Pose-based CNN Features for Action Recognition. Iman Rezazadeh

P-CNN: Pose-based CNN Features for Action Recognition. Iman Rezazadeh P-CNN: Pose-based CNN Features for Action Recognition Iman Rezazadeh Introduction automatic understanding of dynamic scenes strong variations of people and scenes in motion and appearance Fine-grained

More information

Extracting Spatio-temporal Local Features Considering Consecutiveness of Motions

Extracting Spatio-temporal Local Features Considering Consecutiveness of Motions Extracting Spatio-temporal Local Features Considering Consecutiveness of Motions Akitsugu Noguchi and Keiji Yanai Department of Computer Science, The University of Electro-Communications, 1-5-1 Chofugaoka,

More information

EVENT DETECTION AND HUMAN BEHAVIOR RECOGNITION. Ing. Lorenzo Seidenari

EVENT DETECTION AND HUMAN BEHAVIOR RECOGNITION. Ing. Lorenzo Seidenari EVENT DETECTION AND HUMAN BEHAVIOR RECOGNITION Ing. Lorenzo Seidenari e-mail: seidenari@dsi.unifi.it What is an Event? Dictionary.com definition: something that occurs in a certain place during a particular

More information

IMPROVING SPATIO-TEMPORAL FEATURE EXTRACTION TECHNIQUES AND THEIR APPLICATIONS IN ACTION CLASSIFICATION. Maral Mesmakhosroshahi, Joohee Kim

IMPROVING SPATIO-TEMPORAL FEATURE EXTRACTION TECHNIQUES AND THEIR APPLICATIONS IN ACTION CLASSIFICATION. Maral Mesmakhosroshahi, Joohee Kim IMPROVING SPATIO-TEMPORAL FEATURE EXTRACTION TECHNIQUES AND THEIR APPLICATIONS IN ACTION CLASSIFICATION Maral Mesmakhosroshahi, Joohee Kim Department of Electrical and Computer Engineering Illinois Institute

More information

MoSIFT: Recognizing Human Actions in Surveillance Videos

MoSIFT: Recognizing Human Actions in Surveillance Videos MoSIFT: Recognizing Human Actions in Surveillance Videos CMU-CS-09-161 Ming-yu Chen and Alex Hauptmann School of Computer Science Carnegie Mellon University Pittsburgh PA 15213 September 24, 2009 Copyright

More information

CS229: Action Recognition in Tennis

CS229: Action Recognition in Tennis CS229: Action Recognition in Tennis Aman Sikka Stanford University Stanford, CA 94305 Rajbir Kataria Stanford University Stanford, CA 94305 asikka@stanford.edu rkataria@stanford.edu 1. Motivation As active

More information

Action Recognition with HOG-OF Features

Action Recognition with HOG-OF Features Action Recognition with HOG-OF Features Florian Baumann Institut für Informationsverarbeitung, Leibniz Universität Hannover, {last name}@tnt.uni-hannover.de Abstract. In this paper a simple and efficient

More information

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin

More information

A Spatio-Temporal Descriptor Based on 3D-Gradients

A Spatio-Temporal Descriptor Based on 3D-Gradients A Spatio-Temporal Descriptor Based on 3D-Gradients Alexander Kläser Marcin Marszałek Cordelia Schmid INRIA Grenoble, LEAR, LJK {alexander.klaser,marcin.marszalek,cordelia.schmid}@inrialpes.fr Abstract

More information

Understanding Sport Activities from Correspondences of Clustered Trajectories

Understanding Sport Activities from Correspondences of Clustered Trajectories Understanding Sport Activities from Correspondences of Clustered Trajectories Francesco Turchini, Lorenzo Seidenari, Alberto Del Bimbo http://www.micc.unifi.it/vim Introduction The availability of multimedia

More information

People Detection and Video Understanding

People Detection and Video Understanding 1 People Detection and Video Understanding Francois BREMOND INRIA Sophia Antipolis STARS team Institut National Recherche Informatique et Automatisme Francois.Bremond@inria.fr http://www-sop.inria.fr/members/francois.bremond/

More information

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. By Joa õ Carreira and Andrew Zisserman Presenter: Zhisheng Huang 03/02/2018

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. By Joa õ Carreira and Andrew Zisserman Presenter: Zhisheng Huang 03/02/2018 Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset By Joa õ Carreira and Andrew Zisserman Presenter: Zhisheng Huang 03/02/2018 Outline: Introduction Action classification architectures

More information

Long-term Temporal Convolutions for Action Recognition INRIA

Long-term Temporal Convolutions for Action Recognition INRIA Longterm Temporal Convolutions for Action Recognition Gul Varol Ivan Laptev INRIA Cordelia Schmid 2 Motivation Current CNN methods for action recognition learn representations for short intervals (116

More information

Action Recognition & Categories via Spatial-Temporal Features

Action Recognition & Categories via Spatial-Temporal Features Action Recognition & Categories via Spatial-Temporal Features 华俊豪, 11331007 huajh7@gmail.com 2014/4/9 Talk at Image & Video Analysis taught by Huimin Yu. Outline Introduction Frameworks Feature extraction

More information

Action Recognition From Videos using Sparse Trajectories

Action Recognition From Videos using Sparse Trajectories Action Recognition From Videos using Sparse Trajectories Alexandros Doumanoglou, Nicholas Vretos, Petros Daras Centre for Research and Technology - Hellas (ITI-CERTH) 6th Km Charilaou - Thermi, Thessaloniki,

More information

Dense trajectories and motion boundary descriptors for action recognition

Dense trajectories and motion boundary descriptors for action recognition Dense trajectories and motion boundary descriptors for action recognition Heng Wang, Alexander Kläser, Cordelia Schmid, Cheng-Lin Liu To cite this version: Heng Wang, Alexander Kläser, Cordelia Schmid,

More information

Leveraging Textural Features for Recognizing Actions in Low Quality Videos

Leveraging Textural Features for Recognizing Actions in Low Quality Videos Leveraging Textural Features for Recognizing Actions in Low Quality Videos Saimunur Rahman, John See, Chiung Ching Ho Centre of Visual Computing, Faculty of Computing and Informatics Multimedia University,

More information

Class 9 Action Recognition

Class 9 Action Recognition Class 9 Action Recognition Liangliang Cao, April 4, 2013 EECS 6890 Topics in Information Processing Spring 2013, Columbia University http://rogerioferis.com/visualrecognitionandsearch Visual Recognition

More information

Evaluation of local spatio-temporal features for action recognition

Evaluation of local spatio-temporal features for action recognition Evaluation of local spatio-temporal features for action recognition Heng Wang, Muhammad Muneeb Ullah, Alexander Klaser, Ivan Laptev, Cordelia Schmid To cite this version: Heng Wang, Muhammad Muneeb Ullah,

More information

Modeling and visual recognition of human actions and interactions

Modeling and visual recognition of human actions and interactions Modeling and visual recognition of human actions and interactions Ivan Laptev To cite this version: Ivan Laptev. Modeling and visual recognition of human actions and interactions. Computer Vision and Pattern

More information

Spatio-temporal Feature Classifier

Spatio-temporal Feature Classifier Spatio-temporal Feature Classifier Send Orders for Reprints to reprints@benthamscience.ae The Open Automation and Control Systems Journal, 2015, 7, 1-7 1 Open Access Yun Wang 1,* and Suxing Liu 2 1 School

More information

Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach

Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach Vandit Gajjar gajjar.vandit.381@ldce.ac.in Ayesha Gurnani gurnani.ayesha.52@ldce.ac.in Yash Khandhediya khandhediya.yash.364@ldce.ac.in

More information

Deformable Part Models

Deformable Part Models CS 1674: Intro to Computer Vision Deformable Part Models Prof. Adriana Kovashka University of Pittsburgh November 9, 2016 Today: Object category detection Window-based approaches: Last time: Viola-Jones

More information

Large-scale Video Classification with Convolutional Neural Networks

Large-scale Video Classification with Convolutional Neural Networks Large-scale Video Classification with Convolutional Neural Networks Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, Li Fei-Fei Note: Slide content mostly from : Bay Area

More information

Category-level localization

Category-level localization Category-level localization Cordelia Schmid Recognition Classification Object present/absent in an image Often presence of a significant amount of background clutter Localization / Detection Localize object

More information

Fast Realistic Multi-Action Recognition using Mined Dense Spatio-temporal Features

Fast Realistic Multi-Action Recognition using Mined Dense Spatio-temporal Features Fast Realistic Multi-Action Recognition using Mined Dense Spatio-temporal Features Andrew Gilbert, John Illingworth and Richard Bowden CVSSP, University of Surrey, Guildford, Surrey GU2 7XH United Kingdom

More information

Object and Action Detection from a Single Example

Object and Action Detection from a Single Example Object and Action Detection from a Single Example Peyman Milanfar* EE Department University of California, Santa Cruz *Joint work with Hae Jong Seo AFOSR Program Review, June 4-5, 29 Take a look at this:

More information

Robust Action Recognition Using Local Motion and Group Sparsity

Robust Action Recognition Using Local Motion and Group Sparsity Robust Action Recognition Using Local Motion and Group Sparsity Jungchan Cho a, Minsik Lee a, Hyung Jin Chang b, Songhwai Oh a, a Department of Electrical and Computer Engineering and ASRI, Seoul National

More information

Action Localization in Video using a Graph-based Feature Representation

Action Localization in Video using a Graph-based Feature Representation Action Localization in Video using a Graph-based Feature Representation Iveel Jargalsaikhan, Suzanne Little and Noel E O Connor Insight Centre for Data Analytics, Dublin City University, Ireland iveel.jargalsaikhan2@mail.dcu.ie

More information

Learning Representations for Visual Object Class Recognition

Learning Representations for Visual Object Class Recognition Learning Representations for Visual Object Class Recognition Marcin Marszałek Cordelia Schmid Hedi Harzallah Joost van de Weijer LEAR, INRIA Grenoble, Rhône-Alpes, France October 15th, 2007 Bag-of-Features

More information

EasyChair Preprint. Real-Time Action Recognition based on Enhanced Motion Vector Temporal Segment Network

EasyChair Preprint. Real-Time Action Recognition based on Enhanced Motion Vector Temporal Segment Network EasyChair Preprint 730 Real-Time Action Recognition based on Enhanced Motion Vector Temporal Segment Network Xue Bai, Enqing Chen and Haron Chweya Tinega EasyChair preprints are intended for rapid dissemination

More information

Action Recognition in Low Quality Videos by Jointly Using Shape, Motion and Texture Features

Action Recognition in Low Quality Videos by Jointly Using Shape, Motion and Texture Features Action Recognition in Low Quality Videos by Jointly Using Shape, Motion and Texture Features Saimunur Rahman, John See, Chiung Ching Ho Centre of Visual Computing, Faculty of Computing and Informatics

More information

Rich feature hierarchies for accurate object detection and semantic segmentation

Rich feature hierarchies for accurate object detection and semantic segmentation Rich feature hierarchies for accurate object detection and semantic segmentation BY; ROSS GIRSHICK, JEFF DONAHUE, TREVOR DARRELL AND JITENDRA MALIK PRESENTER; MUHAMMAD OSAMA Object detection vs. classification

More information

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Xiaodong Yang, Pavlo Molchanov, Jan Kautz INTELLIGENT VIDEO ANALYTICS Surveillance event detection Human-computer interaction

More information

A Unified Method for First and Third Person Action Recognition

A Unified Method for First and Third Person Action Recognition A Unified Method for First and Third Person Action Recognition Ali Javidani Department of Computer Science and Engineering Shahid Beheshti University Tehran, Iran a.javidani@mail.sbu.ac.ir Ahmad Mahmoudi-Aznaveh

More information

Detecting Parts for Action Localization

Detecting Parts for Action Localization CHESNEAU ET AL.: DETECTING PARTS FOR ACTION LOCALIZATION 1 Detecting Parts for Action Localization Nicolas Chesneau nicolas.chesneau@inria.fr Grégory Rogez gregory.rogez@inria.fr Karteek Alahari karteek.alahari@inria.fr

More information

Dynamic Vision Sensors for Human Activity Recognition

Dynamic Vision Sensors for Human Activity Recognition Dynamic Vision Sensors for Human Activity Recognition Stefanie Anna Baby 1, Bimal Vinod 2, Chaitanya Chinni 3, Kaushik Mitra 4 Computational Imaging Lab IIT Madras, Chennai, India { 1 ee13b120, 2 ee15m005,

More information

Evaluation of local descriptors for action recognition in videos

Evaluation of local descriptors for action recognition in videos Evaluation of local descriptors for action recognition in videos Piotr Bilinski and Francois Bremond INRIA Sophia Antipolis - PULSAR group 2004 route des Lucioles - BP 93 06902 Sophia Antipolis Cedex,

More information

Histogram of Flow and Pyramid Histogram of Visual Words for Action Recognition

Histogram of Flow and Pyramid Histogram of Visual Words for Action Recognition Histogram of Flow and Pyramid Histogram of Visual Words for Action Recognition Ethem F. Can and R. Manmatha Department of Computer Science, UMass Amherst Amherst, MA, 01002, USA [efcan, manmatha]@cs.umass.edu

More information

Local Feature Detectors

Local Feature Detectors Local Feature Detectors Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr Slides adapted from Cordelia Schmid and David Lowe, CVPR 2003 Tutorial, Matthew Brown,

More information

Object detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation

Object detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation Object detection using Region Proposals (RCNN) Ernest Cheung COMP790-125 Presentation 1 2 Problem to solve Object detection Input: Image Output: Bounding box of the object 3 Object detection using CNN

More information

Classification of objects from Video Data (Group 30)

Classification of objects from Video Data (Group 30) Classification of objects from Video Data (Group 30) Sheallika Singh 12665 Vibhuti Mahajan 12792 Aahitagni Mukherjee 12001 M Arvind 12385 1 Motivation Video surveillance has been employed for a long time

More information

arxiv: v2 [cs.cv] 22 Apr 2016

arxiv: v2 [cs.cv] 22 Apr 2016 Improving Human Action Recognition by Non-action Classification Yang Wang and Minh Hoai Stony Brook University, Stony Brook, NY 11794, USA {wang33, minhhoai}@cs.stonybrook.edu arxiv:1604.06397v2 [cs.cv]

More information

Deep learning for object detection. Slides from Svetlana Lazebnik and many others

Deep learning for object detection. Slides from Svetlana Lazebnik and many others Deep learning for object detection Slides from Svetlana Lazebnik and many others Recent developments in object detection 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before deep

More information

Visual Action Recognition

Visual Action Recognition Visual Action Recognition Ying Wu Electrical Engineering and Computer Science Northwestern University, Evanston, IL 60208 yingwu@northwestern.edu http://www.eecs.northwestern.edu/~yingwu 1 / 57 Outline

More information

arxiv: v2 [cs.cv] 31 May 2018

arxiv: v2 [cs.cv] 31 May 2018 Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition Xikun Zhang, Chang Xu, Xinmei Tian, and Dacheng Tao June 1, 2018 arxiv:1805.06184v2 [cs.cv] 31 May 2018 Abstract This paper

More information

1126 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 20, NO. 4, APRIL 2011

1126 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 20, NO. 4, APRIL 2011 1126 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 20, NO. 4, APRIL 2011 Spatiotemporal Localization and Categorization of Human Actions in Unsegmented Image Sequences Antonios Oikonomopoulos, Member, IEEE,

More information

Bag-of-features. Cordelia Schmid

Bag-of-features. Cordelia Schmid Bag-of-features for category classification Cordelia Schmid Visual search Particular objects and scenes, large databases Category recognition Image classification: assigning a class label to the image

More information

MSR-CNN: Applying Motion Salient Region Based Descriptors for Action Recognition

MSR-CNN: Applying Motion Salient Region Based Descriptors for Action Recognition MSR-CNN: Applying Motion Salient Region Based Descriptors for Action Recognition Zhigang Tu School of Computing, Informatics, Decision System Engineering Arizona State University Tempe, USA Email: Zhigang.Tu@asu.edu

More information

Storyline Reconstruction for Unordered Images

Storyline Reconstruction for Unordered Images Introduction: Storyline Reconstruction for Unordered Images Final Paper Sameedha Bairagi, Arpit Khandelwal, Venkatesh Raizaday Storyline reconstruction is a relatively new topic and has not been researched

More information

REALISTIC HUMAN ACTION RECOGNITION: WHEN CNNS MEET LDS

REALISTIC HUMAN ACTION RECOGNITION: WHEN CNNS MEET LDS REALISTIC HUMAN ACTION RECOGNITION: WHEN CNNS MEET LDS Lei Zhang 1, Yangyang Feng 1, Xuezhi Xiang 1, Xiantong Zhen 2 1 College of Information and Communication Engineering, Harbin Engineering University,

More information

Sampling Strategies for Real-time Action Recognition

Sampling Strategies for Real-time Action Recognition 2013 IEEE Conference on Computer Vision and Pattern Recognition Sampling Strategies for Real-time Action Recognition Feng Shi, Emil Petriu and Robert Laganière School of Electrical Engineering and Computer

More information

Eigen-Evolution Dense Trajectory Descriptors

Eigen-Evolution Dense Trajectory Descriptors Eigen-Evolution Dense Trajectory Descriptors Yang Wang, Vinh Tran, and Minh Hoai Stony Brook University, Stony Brook, NY 11794-2424, USA {wang33, tquangvinh, minhhoai}@cs.stonybrook.edu Abstract Trajectory-pooled

More information

Human Action Recognition from Gradient Boundary Histograms

Human Action Recognition from Gradient Boundary Histograms Human Action Recognition from Gradient Boundary Histograms by Xuelu Wang Thesis submitted to the Faculty of Graduate and Postdoctoral Studies In partial fulfillment of the requirements For the M.A.SC.

More information

Vision and Image Processing Lab., CRV Tutorial day- May 30, 2010 Ottawa, Canada

Vision and Image Processing Lab., CRV Tutorial day- May 30, 2010 Ottawa, Canada Spatio-Temporal Salient Features Amir H. Shabani Vision and Image Processing Lab., University of Waterloo, ON CRV Tutorial day- May 30, 2010 Ottawa, Canada 1 Applications Automated surveillance for scene

More information

Action Recognition with Improved Trajectories

Action Recognition with Improved Trajectories Action Recognition with Improved Trajectories Heng Wang and Cordelia Schmid LEAR, INRIA, France firstname.lastname@inria.fr Abstract Recently dense trajectories were shown to be an efficient video representation

More information

Motion Interchange Patterns for Action Recognition in Unconstrained Videos

Motion Interchange Patterns for Action Recognition in Unconstrained Videos Motion Interchange Patterns for Action Recognition in Unconstrained Videos Orit Kliper-Gross, Yaron Gurovich, Tal Hassner, Lior Wolf Weizmann Institute of Science The Open University of Israel Tel Aviv

More information

BSB663 Image Processing Pinar Duygulu. Slides are adapted from Selim Aksoy

BSB663 Image Processing Pinar Duygulu. Slides are adapted from Selim Aksoy BSB663 Image Processing Pinar Duygulu Slides are adapted from Selim Aksoy Image matching Image matching is a fundamental aspect of many problems in computer vision. Object or scene recognition Solving

More information

An evaluation of local action descriptors for human action classification in the presence of occlusion

An evaluation of local action descriptors for human action classification in the presence of occlusion An evaluation of local action descriptors for human action classification in the presence of occlusion Iveel Jargalsaikhan, Cem Direkoglu, Suzanne Little, and Noel E. O Connor INSIGHT Centre for Data Analytics,

More information

AUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering

AUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering AUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering www.csse.uwa.edu.au/~ajmal/ Overview Aim of automatic human action recognition Applications

More information

Detection III: Analyzing and Debugging Detection Methods

Detection III: Analyzing and Debugging Detection Methods CS 1699: Intro to Computer Vision Detection III: Analyzing and Debugging Detection Methods Prof. Adriana Kovashka University of Pittsburgh November 17, 2015 Today Review: Deformable part models How can

More information

Object Detection Based on Deep Learning

Object Detection Based on Deep Learning Object Detection Based on Deep Learning Yurii Pashchenko AI Ukraine 2016, Kharkiv, 2016 Image classification (mostly what you ve seen) http://tutorial.caffe.berkeleyvision.org/caffe-cvpr15-detection.pdf

More information

The SIFT (Scale Invariant Feature

The SIFT (Scale Invariant Feature The SIFT (Scale Invariant Feature Transform) Detector and Descriptor developed by David Lowe University of British Columbia Initial paper ICCV 1999 Newer journal paper IJCV 2004 Review: Matt Brown s Canonical

More information

UNDERSTANDING human actions in videos has been

UNDERSTANDING human actions in videos has been PAPER IDENTIFICATION NUMBER 1 A Space-Time Graph Optimization Approach Based on Maximum Cliques for Action Detection Sunyoung Cho, Member, IEEE, and Hyeran Byun, Member, IEEE Abstract We present an efficient

More information

LEARNING TO SEGMENT MOVING OBJECTS IN VIDEOS FRAGKIADAKI ET AL. 2015

LEARNING TO SEGMENT MOVING OBJECTS IN VIDEOS FRAGKIADAKI ET AL. 2015 LEARNING TO SEGMENT MOVING OBJECTS IN VIDEOS FRAGKIADAKI ET AL. 2015 Darshan Thaker Oct 4, 2017 Problem Statement Moving object segmentation in videos Applications: security tracking, pedestrian detection,

More information

Revisiting LBP-based Texture Models for Human Action Recognition

Revisiting LBP-based Texture Models for Human Action Recognition Revisiting LBP-based Texture Models for Human Action Recognition Thanh Phuong Nguyen 1, Antoine Manzanera 1, Ngoc-Son Vu 2, and Matthieu Garrigues 1 1 ENSTA-ParisTech, 828, Boulevard des Maréchaux, 91762

More information

Mobile Human Detection Systems based on Sliding Windows Approach-A Review

Mobile Human Detection Systems based on Sliding Windows Approach-A Review Mobile Human Detection Systems based on Sliding Windows Approach-A Review Seminar: Mobile Human detection systems Njieutcheu Tassi cedrique Rovile Department of Computer Engineering University of Heidelberg

More information

HUMAN action recognition has received significant research

HUMAN action recognition has received significant research JOURNAL OF L A TEX CLASS FILES, VOL. 6, NO. 1, JANUARY 2007 1 Human Action Recognition in Unconstrained Videos by Explicit Motion Modeling Yu-Gang Jiang, Qi Dai, Wei Liu, Xiangyang Xue, Chong-Wah Ngo Abstract

More information

Object Detection Using Segmented Images

Object Detection Using Segmented Images Object Detection Using Segmented Images Naran Bayanbat Stanford University Palo Alto, CA naranb@stanford.edu Jason Chen Stanford University Palo Alto, CA jasonch@stanford.edu Abstract Object detection

More information

Beyond Bags of features Spatial information & Shape models

Beyond Bags of features Spatial information & Shape models Beyond Bags of features Spatial information & Shape models Jana Kosecka Many slides adapted from S. Lazebnik, FeiFei Li, Rob Fergus, and Antonio Torralba Detection, recognition (so far )! Bags of features

More information

ACTION RECOGNITION USING INTEREST POINTS CAPTURING DIFFERENTIAL MOTION INFORMATION

ACTION RECOGNITION USING INTEREST POINTS CAPTURING DIFFERENTIAL MOTION INFORMATION ACTION RECOGNITION USING INTEREST POINTS CAPTURING DIFFERENTIAL MOTION INFORMATION Gaurav Kumar Yadav, Prakhar Shukla, Amit Sethi Department of Electronics and Electrical Engineering, IIT Guwahati Department

More information

Action Recognition Using Global Spatio-Temporal Features Derived from Sparse Representations

Action Recognition Using Global Spatio-Temporal Features Derived from Sparse Representations Action Recognition Using Global Spatio-Temporal Features Derived from Sparse Representations Guruprasad Somasundaram, Anoop Cherian, Vassilios Morellas, and Nikolaos Papanikolopoulos Department of Computer

More information

QMUL-ACTIVA: Person Runs detection for the TRECVID Surveillance Event Detection task

QMUL-ACTIVA: Person Runs detection for the TRECVID Surveillance Event Detection task QMUL-ACTIVA: Person Runs detection for the TRECVID Surveillance Event Detection task Fahad Daniyal and Andrea Cavallaro Queen Mary University of London Mile End Road, London E1 4NS (United Kingdom) {fahad.daniyal,andrea.cavallaro}@eecs.qmul.ac.uk

More information

Object detection with CNNs

Object detection with CNNs Object detection with CNNs 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before CNNs After CNNs 0% 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 year Region proposals

More information

Feature Descriptors. CS 510 Lecture #21 April 29 th, 2013

Feature Descriptors. CS 510 Lecture #21 April 29 th, 2013 Feature Descriptors CS 510 Lecture #21 April 29 th, 2013 Programming Assignment #4 Due two weeks from today Any questions? How is it going? Where are we? We have two umbrella schemes for object recognition

More information

CS 231A Computer Vision (Fall 2011) Problem Set 4

CS 231A Computer Vision (Fall 2011) Problem Set 4 CS 231A Computer Vision (Fall 2011) Problem Set 4 Due: Nov. 30 th, 2011 (9:30am) 1 Part-based models for Object Recognition (50 points) One approach to object recognition is to use a deformable part-based

More information

Multiple-Choice Questionnaire Group C

Multiple-Choice Questionnaire Group C Family name: Vision and Machine-Learning Given name: 1/28/2011 Multiple-Choice naire Group C No documents authorized. There can be several right answers to a question. Marking-scheme: 2 points if all right

More information

Recognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213)

Recognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213) Recognition of Animal Skin Texture Attributes in the Wild Amey Dharwadker (aap2174) Kai Zhang (kz2213) Motivation Patterns and textures are have an important role in object description and understanding

More information

Learning video saliency from human gaze using candidate selection

Learning video saliency from human gaze using candidate selection Learning video saliency from human gaze using candidate selection Rudoy, Goldman, Shechtman, Zelnik-Manor CVPR 2013 Paper presentation by Ashish Bora Outline What is saliency? Image vs video Candidates

More information

Action Recognition using Discriminative Structured Trajectory Groups

Action Recognition using Discriminative Structured Trajectory Groups 2015 IEEE Winter Conference on Applications of Computer Vision Action Recognition using Discriminative Structured Trajectory Groups Indriyati Atmosukarto 1,2, Narendra Ahuja 3, Bernard Ghanem 4 1 Singapore

More information

Three-Dimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients

Three-Dimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients ThreeDimensional Object Detection and Layout Prediction using Clouds of Oriented Gradients Authors: Zhile Ren, Erik B. Sudderth Presented by: Shannon Kao, Max Wang October 19, 2016 Introduction Given an

More information

Previously. Part-based and local feature models for generic object recognition. Bag-of-words model 4/20/2011

Previously. Part-based and local feature models for generic object recognition. Bag-of-words model 4/20/2011 Previously Part-based and local feature models for generic object recognition Wed, April 20 UT-Austin Discriminative classifiers Boosting Nearest neighbors Support vector machines Useful for object recognition

More information

Robotics Programming Laboratory

Robotics Programming Laboratory Chair of Software Engineering Robotics Programming Laboratory Bertrand Meyer Jiwon Shin Lecture 8: Robot Perception Perception http://pascallin.ecs.soton.ac.uk/challenges/voc/databases.html#caltech car

More information

From Activity to Language:

From Activity to Language: From Activity to Language: Learning to recognise the meaning of motion Centre for Vision, Speech and Signal Processing Prof Rich Bowden 20 June 2011 Overview Talk is about recognising spatio temporal patterns

More information

Stereoscopic Video Description for Human Action Recognition

Stereoscopic Video Description for Human Action Recognition Stereoscopic Video Description for Human Action Recognition Ioannis Mademlis, Alexandros Iosifidis, Anastasios Tefas, Nikos Nikolaidis and Ioannis Pitas Department of Informatics, Aristotle University

More information

Leveraging Textural Features for Recognizing Actions in Low Quality Videos

Leveraging Textural Features for Recognizing Actions in Low Quality Videos Leveraging Textural Features for Recognizing Actions in Low Quality Videos Saimunur Rahman 1, John See 2, and Chiung Ching Ho 3 Centre of Visual Computing, Faculty of Computing and Informatics Multimedia

More information

Tri-modal Human Body Segmentation

Tri-modal Human Body Segmentation Tri-modal Human Body Segmentation Master of Science Thesis Cristina Palmero Cantariño Advisor: Sergio Escalera Guerrero February 6, 2014 Outline 1 Introduction 2 Tri-modal dataset 3 Proposed baseline 4

More information