Social Interactions: A First-Person Perspective.
|
|
- Ella Hodge
- 6 years ago
- Views:
Transcription
1 Social Interactions: A First-Person Perspective. A. Fathi, J. Hodgins, J. Rehg Presented by Jacob Menashe November 16, 2012
2 Social Interaction Detection Objective: Detect social interactions from video footage.
3 Social Interaction Detection Objective: Detect social interactions from video footage. Consider faces and attention
4 Social Interaction Detection Objective: Detect social interactions from video footage. Consider faces and attention Account for temporal context
5 Social Interaction Detection Objective: Detect social interactions from video footage. Consider faces and attention Account for temporal context Analyze first-person movements cues
6 Introduction Overview Features Temporal Context Experiments
7 Video Example Red Yellow Green Light Blue Dark Blue None Dialogue Walking Dialogue Discussion Walking Discussion Monologue Background Link
8 Features Features are constructed based on first- and third-person information.
9 Features Features are constructed based on first- and third-person information. 1. Dense optical flow (first-person movement).
10 Features Features are constructed based on first- and third-person information. 1. Dense optical flow (first-person movement). 2. Face locations (relative to first person)
11 Features Features are constructed based on first- and third-person information. 1. Dense optical flow (first-person movement). 2. Face locations (relative to first person) 3. Attention and Roles. For each person x:
12 Features Features are constructed based on first- and third-person information. 1. Dense optical flow (first-person movement). 2. Face locations (relative to first person) 3. Attention and Roles. For each person x: Faces looking at x
13 Features Features are constructed based on first- and third-person information. 1. Dense optical flow (first-person movement). 2. Face locations (relative to first person) 3. Attention and Roles. For each person x: Faces looking at x Whether first person looks at x
14 Features Features are constructed based on first- and third-person information. 1. Dense optical flow (first-person movement). 2. Face locations (relative to first person) 3. Attention and Roles. For each person x: Faces looking at x Whether first person looks at x Mutual attention between x and first person
15 Features Features are constructed based on first- and third-person information. 1. Dense optical flow (first-person movement). 2. Face locations (relative to first person) 3. Attention and Roles. For each person x: Faces looking at x Whether first person looks at x Mutual attention between x and first person Number of faces looking at where x is looking
16 Feature Example
17 Conditional Random Fields CRFs are described in Lafferty et al. [2001].
18 Conditional Random Fields CRFs are described in Lafferty et al. [2001]. Observations and labels form a Markov chain. Nodes pend on neighbors. y 1 y 2 y 3 x 1 x 2 x 3
19 Conditional Random Fields CRFs are described in Lafferty et al. [2001]. Observations and labels form a Markov chain. Nodes pend on neighbors. y 1 y 1 y 2 y 3 p(y 1 x 1, y 2 ) x 1 x 2 x 3
20 Conditional Random Fields CRFs are described in Lafferty et al. [2001]. Observations and labels form a Markov chain. Nodes pend on neighbors. y 1 y 2 y 3 p(y 2 y 1, y 3, x 2 ) x 1 x 2 x 3
21 Conditional Random Fields CRFs are described in Lafferty et al. [2001]. Observations and labels form a Markov chain. Nodes pend on neighbors. y 3 y 1 y 2 y 3 p(y 3 y 2, x 3 ) x 1 x 2 x 3
22 Hidden Conditional Random Fields A micro view of the HCRF model as described in Quattoni et al. [2007]. Y h 1 h 2 h 3 x i
23 Hidden Conditional Random Fields A micro view of the HCRF model as described in Quattoni et al. [2007]. Y is a label for the whole sequence. Y h 1 h 2 h 3 x i
24 Hidden Conditional Random Fields A micro view of the HCRF model as described in Quattoni et al. [2007]. Y is a label for the whole sequence. x i is a single observation in the sequence. Y h 1 h 2 h 3 x i
25 Hidden Conditional Random Fields A micro view of the HCRF model as described in Quattoni et al. [2007]. Y is a label for the whole sequence. x i is a single observation in the sequence. Each h i is a possible hidden state. Y h 1 h 2 h 3 x i
26 Hidden Conditional Random Fields (cont.) A macro view of the HCRF model as described in Quattoni et al. [2007]. Y h 1 h 2 h 3 x 1 x 2 x 3
27 Hidden Conditional Random Fields (cont.) A macro view of the HCRF model as described in Quattoni et al. [2007]. Y is a label for the whole sequence. Y h 1 h 2 h 3 x 1 x 2 x 3
28 Hidden Conditional Random Fields (cont.) A macro view of the HCRF model as described in Quattoni et al. [2007]. Y is a label for the whole sequence. Each x i is a single observation in the sequence. Y h 1 h 2 h 3 x 1 x 2 x 3
29 Hidden Conditional Random Fields (cont.) A macro view of the HCRF model as described in Quattoni et al. [2007]. Y is a label for the whole sequence. Each x i is a single observation in the sequence. Each h i is the hidden state label assigned to x i. Y h 1 h 2 h 3 x 1 x 2 x 3
30 Hidden Conditional Random Fields (cont.) A macro view of the HCRF model as described in Quattoni et al. [2007]. Y is a label for the whole sequence. Each x i is a single observation in the sequence. Each h i is the hidden state label assigned to x i. Y p(h 1 Y, h 2, x 1 ) h 1 h 2 h 3 x 1 x 2 x 3
31 Hidden Conditional Random Fields (cont.) A macro view of the HCRF model as described in Quattoni et al. [2007]. Y is a label for the whole sequence. Each x i is a single observation in the sequence. Each h i is the hidden state label assigned to x i. Y p(h 2 Y, h 1, h 3, x 2 ) h 1 h 2 h 3 x 1 x 2 x 3
32 Hidden Conditional Random Fields (cont.) A macro view of the HCRF model as described in Quattoni et al. [2007]. Y is a label for the whole sequence. Each x i is a single observation in the sequence. Each h i is the hidden state label assigned to x i. Y p(h 3 Y, h 2, x 3 ) h 1 h 2 h 3 x 1 x 2 x 3
33 Hidden Conditional Random Fields (cont.) A macro view of the HCRF model as described in Quattoni et al. [2007]. Y is a label for the whole sequence. Each x i is a single observation in the sequence. Each h i is the hidden state label assigned to x i. Y p(y {h i }) = p(y {x i }) h 1 h 2 h 3 x 1 x 2 x 3
34 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). WDlg h 1 h 2 h 3 x 1 x 2 x 3
35 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. WDlg h 1 h 2 h 3 x 1 x 2 x 3
36 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. Each h i is determined from training: WDlg h 1 h 2 h 3 x 1 x 2 x 3
37 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. Each h i is determined from training: h1 : John wants to hear about my weekend. WDlg h 1 h 1 h 2 h 3 x 1 x 2 x 3
38 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. Each h i is determined from training: h 2 : I m feeling talkative. WDlg h 2 h 1 h 2 h 3 x 1 x 2 x 3
39 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. Each h i is determined from training: h 3 : Mary wants to listen to her ipod. WDlg h 3 h 1 h 2 h 3 x 1 x 2 x 3
40 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. Each h i is determined from training: h1 : John wants to hear about my weekend. WDlg p(h 1 Y, h 2, x 1 ) h 1 h 2 h 3 x 1 x 2 x 3
41 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. Each h i is determined from training: h 2 : I m feeling talkative. WDlg p(h 2 Y, h 1, h 3, x 2 ) h 1 h 2 h 3 x 1 x 2 x 3
42 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. Each h i is determined from training: h 3 : Mary wants to listen to her ipod. WDlg p(h 3 Y, h 2, x 3 ) h 1 h 2 h 3 x 1 x 2 x 3
43 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. Each h i is determined from training: h1 : John wants to hear about my weekend. h 2 : I m feeling talkative. h 3 : Mary wants to listen to her ipod. WDlg p(wdlg {h i }) = p(wdlg {x i }) h 1 h 2 h 3 x 1 x 2 x 3
44 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. Each h i is determined from training: h1 : John wants to hear about my weekend. h 2 : I m feeling talkative. h 3 : Mary wants to listen to her ipod. WDisc WDlg p(wdisc {h i }) = p(wdisc {x i }) h 1 h 2 h 3 x 1 x 2 x 3
45 HCRF Example Suppose we want to find the likelihood of walking dialogue (WDlg) vs walking discussion (WDisc). Each x i is now a feature extracted from video frames. Each h i is determined from training: h1 : John wants to hear about my weekend. h 2 : I m feeling talkative. h 3 : Mary wants to listen to her ipod. Y If p(wdlg) > p(wdisc), assign Y = WDlg. h 1 h 2 h 3 x 1 x 2 x 3
46 Introduction Overview Temporal Context Conditional Random Fields Hidden Conditional Random Fields HCRF Example Experiments
47 Introduction Overview Temporal Context Experiments Experiment Outline Experiment 1: Video Processing Experiment 2: Caltech Dataset Conclusion
48 Experiment Outline The following experiments are presented:
49 Experiment Outline The following experiments are presented: Video Processing
50 Experiment Outline The following experiments are presented: Video Processing Caltech image dataset
51 Experiment Outline The following experiments are presented: Video Processing Caltech image dataset Adjusted parameters:
52 Experiment Outline The following experiments are presented: Video Processing Caltech image dataset Adjusted parameters: Iterations
53 Experiment Outline The following experiments are presented: Video Processing Caltech image dataset Adjusted parameters: Iterations Hidden States
54 Experiment Outline The following experiments are presented: Video Processing Caltech image dataset Adjusted parameters: Iterations Hidden States Optimization Function
55 Experiment Outline The following experiments are presented: Video Processing Caltech image dataset Adjusted parameters: Iterations Hidden States Optimization Function Clusters
56 Experiment Outline The following experiments are presented: Video Processing Caltech image dataset Adjusted parameters: Iterations Hidden States Optimization Function Clusters Compared with linear SVM baseline
57 Experiment 1: Video Processing Mine Theirs 40 training intervals 4,000 training intervals 40 testing intervals [unspecified] Dialogue vs Discussion One vs. All All Features Location First-Person Motion Attention All Features
58 Experiment 1: Video Processing Mine Theirs 40 training intervals 4,000 training intervals 40 testing intervals [unspecified] Dialogue vs Discussion One vs. All All Features Location First-Person Motion Attention All Features ~42 hours = 11,340 intervals 11, hours per 20 intervals > 18 months
59 Experiment 1: Video Processing (cont.) My Results Their Results 1 HCRF Dialogue vs Discussion Detection True positive rate False positive rate
60 Experiment 2: Caltech Dataset Experiment 2 focuses on the Caltech image dataset.
61 Experiment 2: Caltech Dataset Experiment 2 focuses on the Caltech image dataset. Multi-class HCRF evaluated
62 Experiment 2: Caltech Dataset Experiment 2 focuses on the Caltech image dataset. Multi-class HCRF evaluated Classes are evaluated in isolation.
63 Experiment 2: Caltech Dataset Experiment 2 focuses on the Caltech image dataset. Multi-class HCRF evaluated Classes are evaluated in isolation. Temporal context is simulated with clustering
64 Experiment 2: Caltech Dataset Experiment 2 focuses on the Caltech image dataset. Multi-class HCRF evaluated Classes are evaluated in isolation. Temporal context is simulated with clustering Initial parameters are based on Fathi et al. [2012]:
65 Experiment 2: Caltech Dataset Experiment 2 focuses on the Caltech image dataset. Multi-class HCRF evaluated Classes are evaluated in isolation. Temporal context is simulated with clustering Initial parameters are based on Fathi et al. [2012]: Hidden States: 5
66 Experiment 2: Caltech Dataset Experiment 2 focuses on the Caltech image dataset. Multi-class HCRF evaluated Classes are evaluated in isolation. Temporal context is simulated with clustering Initial parameters are based on Fathi et al. [2012]: Hidden States: 5 Window Size: 5
67 Experiment 2: Caltech Dataset Experiment 2 focuses on the Caltech image dataset. Multi-class HCRF evaluated Classes are evaluated in isolation. Temporal context is simulated with clustering Initial parameters are based on Fathi et al. [2012]: Hidden States: 5 Window Size: 5 Max Iterations: 100
68 Experiment 2: Caltech Dataset Experiment 2 focuses on the Caltech image dataset. Multi-class HCRF evaluated Classes are evaluated in isolation. Temporal context is simulated with clustering Initial parameters are based on Fathi et al. [2012]: Hidden States: 5 Window Size: 5 Max Iterations: 100 Optimizer: Broyden Fletcher-Goldfarb-Shanno (BFGS)
69 Exp. 2a: Initial Settings test airplanes HCRF cars HCRF faces HCRF motorbikes HCRF svm (all) 0.7 True positive rate False positive rate Processing: ~18 minutes, 1 MB
70 Exp. 2a: Initial Settings (cont.) airplanes rank 1 rank 2 rank 3 rank 4 motorbikes faces cars
71 Exp. 2b: Low Iterations HCRF with 10 iterations airplanes HCRF cars HCRF faces HCRF motorbikes HCRF 0.7 True positive rate False positive rate Processing: ~3 minutes, 1 MB
72 Exp. 2c: Low Hidden States HCRF with 1 Hidden State airplanes HCRF cars HCRF faces HCRF motorbikes HCRF 0.7 True positive rate False positive rate Processing: ~2 minutes, 1 MB
73 Exp. 2d: CG Optimizer HCRF with Conjugate Gradient Optimizer airplanes HCRF cars HCRF faces HCRF motorbikes HCRF 0.7 True positive rate False positive rate Processing: ~11 minutes, 1 MB
74 Exp. 2e: Increased Iterations HCRF with 1000 iterations airplanes HCRF cars HCRF faces HCRF motorbikes HCRF 0.7 True positive rate False positive rate Processing: ~30 minutes, 1 MB
75 Exp. 2f: Increased Hidden States HCRF with 15 Hidden States airplanes HCRF cars HCRF faces HCRF motorbikes HCRF 0.7 True positive rate False positive rate Processing: ~1 hour, 3 GB
76 Exp. 2g: Clustering + 15 Hidden States HCRF with Clustering and 15 Hidden States airplanes HCRF cars HCRF faces HCRF motorbikes HCRF 0.7 True positive rate False positive rate Processing: ~1 hour 10 minutes, 3 GB
77 Exp. 2g: Clustering + 15 Hidden States (cont.) rank 1 rank 2 rank 3 rank 4 motorbikes faces cars airplanes
78 Exp. 2h: Clustering + 20 Hidden States HCRF with Clustering and 20 Hidden States airplanes HCRF cars HCRF faces HCRF motorbikes HCRF 0.7 True positive rate False positive rate Processing: ~1 hour 40 minutes, 5 GB
79 Exp. 2i: LDCRF with 20 Hidden States LDCRF with Clustering and 20 Hidden States airplanes LDCRF cars LDCRF faces LDCRF motorbikes LDCRF 0.7 True positive rate False positive rate Processing: ~5 hours 20 minutes, 5 GB
80 Exp. 2j: CRF with Initial Parameters CRF with Clustering airplanes CRF cars CRF faces CRF motorbikes CRF 0.7 True positive rate False positive rate Processing: ~21 seconds, 1 MB
81 Exp. 2j: CRF with Initial Parameters (cont.) rank 1 rank 2 rank 3 rank 4 motorbikes faces cars airplanes
82 Overall Results SVM, CRF, and LDCRF perform best
83 Overall Results SVM, CRF, and LDCRF perform best CRF almost outperforms all with negligible memory and processing requirements
84 Overall Results SVM, CRF, and LDCRF perform best CRF almost outperforms all with negligible memory and processing requirements Hidden states increase accuracy but at significant memory cost
85 Conclusion HCRF is accurate, but has a heavy performance cost. May be optimal for particular domains.
86 References I Alireza Fathi, Jessica K. Hodgins, and James M. Rehg. Social interactions: A first-person perspective. In CVPR, pages IEEE, ISBN URL cvpr2012.html#fathihr12. John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the Eighteenth International Conference on Machine Learning, ICML 01, pages , San Francisco, CA, USA, Morgan Kaufmann Publishers Inc. ISBN URL http: //dl.acm.org/citation.cfm?id=
87 References II Ariadna Quattoni, Sybor Wang, Louis-Philippe Morency, Michael Collins, and Trevor Darrell. Hidden conditional random fields. IEEE Trans. Pattern Anal. Mach. Intell., 29 (10): , October ISSN doi: /TPAMI URL
Training LDCRF model on unsegmented sequences using Connectionist Temporal Classification
Training LDCRF model on unsegmented sequences using Connectionist Temporal Classification 1 Amir Ahooye Atashin, 2 Kamaledin Ghiasi-Shirazi, 3 Ahad Harati Department of Computer Engineering Ferdowsi University
More informationarxiv: v1 [cs.ne] 6 Oct 2016
Sequence-based Sleep Stage Classification using Conditional Neural Fields Intan Nurma Yulita 1,2, Mohamad Ivan Fanany 1, Aniati Murni Arymurthy 1, arxiv:1610.01935v1 [cs.ne] 6 Oct 2016 1 Machine Learning
More informationarxiv: v1 [cs.cv] 19 Jun 2015
CROWD FLOW SEGMENTATION IN COMPRESSED DOMAIN USING CRF Srinivas S S Kruthiventi and R. Venkatesh Babu Video Analytics Lab Supercomputer Education and Research Centre Indian Institute of Science, Bangalore,
More informationCS 6784 Paper Presentation
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data John La erty, Andrew McCallum, Fernando C. N. Pereira February 20, 2014 Main Contributions Main Contribution Summary
More informationConditional Random Fields for Object Recognition
Conditional Random Fields for Object Recognition Ariadna Quattoni Michael Collins Trevor Darrell MIT Computer Science and Artificial Intelligence Laboratory Cambridge, MA 02139 {ariadna, mcollins, trevor}@csail.mit.edu
More informationSequential Emotion Recognition using Latent-Dynamic Conditional Neural Fields
Sequential Emotion Recognition using Latent-Dynamic Conditional Neural Fields Julien-Charles Lévesque Louis-Philippe Morency Christian Gagné Abstract A wide number of problems in face and gesture analysis
More informationConditional Random Fields : Theory and Application
Conditional Random Fields : Theory and Application Matt Seigel (mss46@cam.ac.uk) 3 June 2010 Cambridge University Engineering Department Outline The Sequence Classification Problem Linear Chain CRFs CRF
More informationLatent-Dynamic Discriminative Models for Continuous Gesture Recognition Louis-Philippe Morency, Ariadna Quattoni, and Trevor Darrell
Computer Science and Artificial Intelligence Laboratory Technical Report MIT-CSAIL-TR-2007-002 January 7, 2007 Latent-Dynamic Discriminative Models for Continuous Gesture Recognition Louis-Philippe Morency,
More informationCRFs for Image Classification
CRFs for Image Classification Devi Parikh and Dhruv Batra Carnegie Mellon University Pittsburgh, PA 15213 {dparikh,dbatra}@ece.cmu.edu Abstract We use Conditional Random Fields (CRFs) to classify regions
More informationComplexity-Aware Assignment of Latent Values in Discriminative Models for Accurate Gesture Recognition
Complexity-Aware Assignment of Latent Values in Discriminative Models for Accurate Gesture Recognition Manoel Horta Ribeiro, Bruno Teixeira, Antônio Otávio Fernandes, Wagner Meira Jr., Erickson R. Nascimento
More informationSign Language Recognition using Dynamic Time Warping and Hand Shape Distance Based on Histogram of Oriented Gradient Features
Sign Language Recognition using Dynamic Time Warping and Hand Shape Distance Based on Histogram of Oriented Gradient Features Pat Jangyodsuk Department of Computer Science and Engineering The University
More informationConditional Random Fields - A probabilistic graphical model. Yen-Chin Lee 指導老師 : 鮑興國
Conditional Random Fields - A probabilistic graphical model Yen-Chin Lee 指導老師 : 鮑興國 Outline Labeling sequence data problem Introduction conditional random field (CRF) Different views on building a conditional
More informationLow-dimensional Representations of Hyperspectral Data for Use in CRF-based Classification
Rochester Institute of Technology RIT Scholar Works Presentations and other scholarship 8-31-2015 Low-dimensional Representations of Hyperspectral Data for Use in CRF-based Classification Yang Hu Nathan
More informationObject Recognition with Latent Conditional Random Fields. Ariadna Quattoni
Object Recognition with Latent Conditional Random Fields by Ariadna Quattoni Submitted to the Department of Electrical Engineering and Computer Science in partial fulfillment of the requirements for the
More informationCS545 Project: Conditional Random Fields on an ecommerce Website
CS545 Project: Conditional Random Fields on an ecommerce Website Brock Wilcox December 18, 2013 Contents 1 Conditional Random Fields 1 1.1 Overview................................................. 1 1.2
More informationFeature Extraction and Loss training using CRFs: A Project Report
Feature Extraction and Loss training using CRFs: A Project Report Ankan Saha Department of computer Science University of Chicago March 11, 2008 Abstract POS tagging has been a very important problem in
More informationA Hierarchical Model for Human Interaction Recognition
A Hierarchical Model for Human Interaction Recognition Yu Kong and Yunde Jia Beijing Laboratory of Intelligent Information Technology School of Computer Science, Beijing Institute of Technology Beijing
More informationConditional Random Fields for Word Hyphenation
Conditional Random Fields for Word Hyphenation Tsung-Yi Lin and Chen-Yu Lee Department of Electrical and Computer Engineering University of California, San Diego {tsl008, chl260}@ucsd.edu February 12,
More informationStructured Learning. Jun Zhu
Structured Learning Jun Zhu Supervised learning Given a set of I.I.D. training samples Learn a prediction function b r a c e Supervised learning (cont d) Many different choices Logistic Regression Maximum
More informationJoint Inference in Image Databases via Dense Correspondence. Michael Rubinstein MIT CSAIL (while interning at Microsoft Research)
Joint Inference in Image Databases via Dense Correspondence Michael Rubinstein MIT CSAIL (while interning at Microsoft Research) My work Throughout the year (and my PhD thesis): Temporal Video Analysis
More informationComputationally Efficient M-Estimation of Log-Linear Structure Models
Computationally Efficient M-Estimation of Log-Linear Structure Models Noah Smith, Doug Vail, and John Lafferty School of Computer Science Carnegie Mellon University {nasmith,dvail2,lafferty}@cs.cmu.edu
More informationConditional Random Field for tracking user behavior based on his eye s movements 1
Conditional Random Field for tracing user behavior based on his eye s movements 1 Trinh Minh Tri Do Thierry Artières LIP6, Université Paris 6 LIP6, Université Paris 6 8 rue du capitaine Scott 8 rue du
More informationHadoopPerceptron: a Toolkit for Distributed Perceptron Training and Prediction with MapReduce
HadoopPerceptron: a Toolkit for Distributed Perceptron Training and Prediction with MapReduce Andrea Gesmundo Computer Science Department University of Geneva Geneva, Switzerland andrea.gesmundo@unige.ch
More informationDetecting Coarticulation in Sign Language using Conditional Random Fields
Detecting Coarticulation in Sign Language using Conditional Random Fields Ruiduo Yang and Sudeep Sarkar Computer Science and Engineering Department University of South Florida 4202 E. Fowler Ave. Tampa,
More informationSegmentation of Video Sequences using Spatial-temporal Conditional Random Fields
Segmentation of Video Sequences using Spatial-temporal Conditional Random Fields Lei Zhang and Qiang Ji Rensselaer Polytechnic Institute 110 8th St., Troy, NY 12180 {zhangl2@rpi.edu,qji@ecse.rpi.edu} Abstract
More informationHiRF: Hierarchical Random Field for Collective Activity Recognition in Videos
HiRF: Hierarchical Random Field for Collective Activity Recognition in Videos Mohamed R. Amer, Peng Lei, Sinisa Todorovic Oregon State University School of Electrical Engineering and Computer Science {amerm,
More informationLearning bottom-up visual processes using automatically generated ground truth data
Learning bottom-up visual processes using automatically generated ground truth data Kalle Åström, Yubin Kuang, Magnus Oskarsson, Lars Kopp an Martin Byröd Mathematical Imaging Group Center for Mathematical
More informationJOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS. Puyang Xu, Ruhi Sarikaya. Microsoft Corporation
JOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS Puyang Xu, Ruhi Sarikaya Microsoft Corporation ABSTRACT We describe a joint model for intent detection and slot filling based
More informationResearch Article Contextual Hierarchical Part-Driven Conditional Random Field Model for Object Category Detection
Mathematical Problems in Engineering Volume 2012, Article ID 671397, 13 pages doi:10.1155/2012/671397 Research Article Contextual Hierarchical Part-Driven Conditional Random Field Model for Object Category
More informationDetection of Mitosis within a Stem Cell Population of High Cell Confluence in Phase-Contrast Microscopy Images
Detection of Mitosis within a Stem Cell Population of High Cell Confluence in Phase-Contrast Microscopy Images Seungil Huh Robotics Institute Carnegie Mellon University 5000 Forbes Ave. Pittsburgh, PA15213
More informationAction Recognition by Hierarchical Sequence Summarization
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 013. Action Recognition by Hierarchical Sequence Summarization Yale Song 1, Louis-Philippe Morency, Randall Davis 1 1 MIT Computer Science
More informationSurveillance Event Detection
Surveillance Event Detection Mert Dikmen, Huazhong Ning, Dennis J. Lin, Liangliang Cao, Vuong Le, Shen-Fu Tsai, Kai-Hsiang Lin, Zhen Li, Jianchao Yang, Thomas S. Huang Department of Electrical and Computer
More informationConditional Random Fields and beyond D A N I E L K H A S H A B I C S U I U C,
Conditional Random Fields and beyond D A N I E L K H A S H A B I C S 5 4 6 U I U C, 2 0 1 3 Outline Modeling Inference Training Applications Outline Modeling Problem definition Discriminative vs. Generative
More informationGradient of the lower bound
Weakly Supervised with Latent PhD advisor: Dr. Ambedkar Dukkipati Department of Computer Science and Automation gaurav.pandey@csa.iisc.ernet.in Objective Given a training set that comprises image and image-level
More informationLearning Diagram Parts with Hidden Random Fields
Learning Diagram Parts with Hidden Random Fields Martin Szummer Microsoft Research Cambridge, CB 0FB, United Kingdom szummer@microsoft.com Abstract Many diagrams contain compound objects composed of parts.
More informationDiscriminative human action recognition using pairwise CSP classifiers
Discriminative human action recognition using pairwise CSP classifiers Ronald Poppe and Mannes Poel University of Twente, Dept. of Computer Science, Human Media Interaction Group P.O. Box 217, 7500 AE
More informationInternational Journal of Electrical, Electronics ISSN No. (Online): and Computer Engineering 3(2): 85-90(2014)
I J E E E C International Journal of Electrical, Electronics ISSN No. (Online): 2277-2626 Computer Engineering 3(2): 85-90(2014) Robust Approach to Recognize Localize Text from Natural Scene Images Khushbu
More informationBRAIN computer interfaces (BCI) are systems that. Discriminative Methods for Classification of Asynchronous Imaginary Motor Tasks from EEG Data
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 1 Discriminative Methods for Classification of Asynchronous Imaginary Motor Tasks from EEG Data Jaime F. Delgado Saa, Student member,
More informationCRF Feature Induction
CRF Feature Induction Andrew McCallum Efficiently Inducing Features of Conditional Random Fields Kuzman Ganchev 1 Introduction Basic Idea Aside: Transformation Based Learning Notation/CRF Review 2 Arbitrary
More informationDeformable 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 informationGrounded Compositional Semantics for Finding and Describing Images with Sentences
Grounded Compositional Semantics for Finding and Describing Images with Sentences R. Socher, A. Karpathy, V. Le,D. Manning, A Y. Ng - 2013 Ali Gharaee 1 Alireza Keshavarzi 2 1 Department of Computational
More informationSegmentation and labeling of documents using Conditional Random Fields
Segmentation and labeling of documents using Conditional Random Fields Shravya Shetty, Harish Srinivasan, Matthew Beal and Sargur Srihari Center of Excellence for Document Analysis and Recognition (CEDAR)
More informationAutomatic Domain Partitioning for Multi-Domain Learning
Automatic Domain Partitioning for Multi-Domain Learning Di Wang diwang@cs.cmu.edu Chenyan Xiong cx@cs.cmu.edu William Yang Wang ww@cmu.edu Abstract Multi-Domain learning (MDL) assumes that the domain labels
More informationRobust Place Recognition with Stereo Cameras
Robust Place Recognition with Stereo Cameras César Cadena, Dorian Gálvez-López, Fabio Ramos, Juan D. Tardós and José Neira Abstract Place recognition is a challenging task in any SLAM system. Algorithms
More informationLarge Displacement Optical Flow & Applications
Large Displacement Optical Flow & Applications Narayanan Sundaram, Kurt Keutzer (Parlab) In collaboration with Thomas Brox (University of Freiburg) Michael Tao (University of California Berkeley) Parlab
More informationTraining Restricted Boltzmann Machines using Approximations to the Likelihood Gradient. Ali Mirzapour Paper Presentation - Deep Learning March 7 th
Training Restricted Boltzmann Machines using Approximations to the Likelihood Gradient Ali Mirzapour Paper Presentation - Deep Learning March 7 th 1 Outline of the Presentation Restricted Boltzmann Machine
More informationNeural Network and Deep Learning. Donglin Zeng, Department of Biostatistics, University of North Carolina
Neural Network and Deep Learning Early history of deep learning Deep learning dates back to 1940s: known as cybernetics in the 1940s-60s, connectionism in the 1980s-90s, and under the current name starting
More informationMetric Learning for Large-Scale Image Classification:
Metric Learning for Large-Scale Image Classification: Generalizing to New Classes at Near-Zero Cost Florent Perronnin 1 work published at ECCV 2012 with: Thomas Mensink 1,2 Jakob Verbeek 2 Gabriela Csurka
More informationTrajectory analysis. Ivan Kukanov
Trajectory analysis Ivan Kukanov Joensuu, 2014 Semantic Trajectory Mining for Location Prediction Josh Jia-Ching Ying Tz-Chiao Weng Vincent S. Tseng Taiwan Wang-Chien Lee Wang-Chien Lee USA Copyright 2011
More informationA Probabilistic Graphical Model-based Approach for Minimizing Energy under Performance Constraints
A Probabilistic Graphical Model-based Approach for Minimizing Energy under Performance Constraints Nikita Mishra, Huazhe Zhang, John Lafferty and Hank Hoffmann University of Chicago Fraction of time CPU
More informationDetection 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 informationA Note on Semi-Supervised Learning using Markov Random Fields
A Note on Semi-Supervised Learning using Markov Random Fields Wei Li and Andrew McCallum {weili, mccallum}@cs.umass.edu Computer Science Department University of Massachusetts Amherst February 3, 2004
More informationDiscriminative classifiers for image recognition
Discriminative classifiers for image recognition May 26 th, 2015 Yong Jae Lee UC Davis Outline Last time: window-based generic object detection basic pipeline face detection with boosting as case study
More informationExtracting and Querying Probabilistic Information From Text in BayesStore-IE
Extracting and Querying Probabilistic Information From Text in BayesStore-IE Daisy Zhe Wang, Michael J. Franklin, Minos Garofalakis 2, Joseph M. Hellerstein University of California, Berkeley Technical
More informationPart-based and local feature models for generic object recognition
Part-based and local feature models for generic object recognition May 28 th, 2015 Yong Jae Lee UC Davis Announcements PS2 grades up on SmartSite PS2 stats: Mean: 80.15 Standard Dev: 22.77 Vote on piazza
More informationBUPT at TREC 2009: Entity Track
BUPT at TREC 2009: Entity Track Zhanyi Wang, Dongxin Liu, Weiran Xu, Guang Chen, Jun Guo Pattern Recognition and Intelligent System Lab, Beijing University of Posts and Telecommunications, Beijing, China,
More informationDeep Web Crawling and Mining for Building Advanced Search Application
Deep Web Crawling and Mining for Building Advanced Search Application Zhigang Hua, Dan Hou, Yu Liu, Xin Sun, Yanbing Yu {hua, houdan, yuliu, xinsun, yyu}@cc.gatech.edu College of computing, Georgia Tech
More informationClinical Name Entity Recognition using Conditional Random Field with Augmented Features
Clinical Name Entity Recognition using Conditional Random Field with Augmented Features Dawei Geng (Intern at Philips Research China, Shanghai) Abstract. In this paper, We presents a Chinese medical term
More informationECLT 5810 Clustering
ECLT 5810 Clustering What is Cluster Analysis? Cluster: a collection of data objects Similar to one another within the same cluster Dissimilar to the objects in other clusters Cluster analysis Grouping
More informationSupport Vector Machine-Based Human Behavior Classification in Crowd through Projection and Star Skeletonization
Journal of Computer Science 6 (9): 1008-1013, 2010 ISSN 1549-3636 2010 Science Publications Support Vector Machine-Based Human Behavior Classification in Crowd through Projection and Star Skeletonization
More informationCAP 6412 Advanced Computer Vision
CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 21st, 2016 Today Administrivia Free parameters in an approach, model, or algorithm? Egocentric videos by Aisha
More informationBias-Variance Trade-off + Other Models and Problems
CS 1699: Intro to Computer Vision Bias-Variance Trade-off + Other Models and Problems Prof. Adriana Kovashka University of Pittsburgh November 3, 2015 Outline Support Vector Machines (review + other uses)
More informationHidden Markov Models. Slides adapted from Joyce Ho, David Sontag, Geoffrey Hinton, Eric Xing, and Nicholas Ruozzi
Hidden Markov Models Slides adapted from Joyce Ho, David Sontag, Geoffrey Hinton, Eric Xing, and Nicholas Ruozzi Sequential Data Time-series: Stock market, weather, speech, video Ordered: Text, genes Sequential
More informationPlace Recognition using Near and Far Visual Information
Place Recognition using Near and Far Visual Information César Cadena John McDonald John J. Leonard José Neira Instituto de Investigación en Ingeniería de Aragón (I3A), Universidad de Zaragoza, Zaragoza
More informationTheoretical Concepts of Machine Learning
Theoretical Concepts of Machine Learning Part 2 Institute of Bioinformatics Johannes Kepler University, Linz, Austria Outline 1 Introduction 2 Generalization Error 3 Maximum Likelihood 4 Noise Models 5
More informationSpanning Tree Approximations for Conditional Random Fields
Patrick Pletscher Department of Computer Science ETH Zurich, Switzerland pletscher@inf.ethz.ch Cheng Soon Ong Department of Computer Science ETH Zurich, Switzerland chengsoon.ong@inf.ethz.ch Joachim M.
More informationLocated Hidden Random Fields: Learning Discriminative Parts for Object Detection
Located Hidden Random Fields: Learning Discriminative Parts for Object Detection Ashish Kapoor 1 and John Winn 2 1 MIT Media Laboratory, Cambridge, MA 02139, USA kapoor@media.mit.edu 2 Microsoft Research,
More informationPlace Recognition using Near and Far Visual Information
Place Recognition using Near and Far Visual Information César Cadena John McDonald John J. Leonard José Neira Instituto de Investigación en Ingeniería de Aragón (I3A), Universidad de Zaragoza, Zaragoza
More informationLeveraging 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 informationSpatio-Temporal Event Detection Using Dynamic Conditional Random Fields
Spatio-Temporal Event Detection Using Dynamic Conditional Random Fields Jie Yin Information Engineering Laboratory CSIRO ICT Centre Australia jie.yin@csiro.au Derek Hao Hu and Qiang Yang Department of
More information2 Signature-Based Retrieval of Scanned Documents Using Conditional Random Fields
2 Signature-Based Retrieval of Scanned Documents Using Conditional Random Fields Harish Srinivasan and Sargur Srihari Summary. In searching a large repository of scanned documents, a task of interest is
More informationTemporal Models for Robot Classification of Human Interruptibility
Temporal Models for Robot Classification of Human Interruptibility ABSTRACT Siddhartha Banerjee Georgia Institute of Technology 801 Atlantic Dr NW Atlanta, GA 30332, USA siddhartha.banerjee@gatech.edu
More informationLearning Spatial Context: Using Stuff to Find Things
Learning Spatial Context: Using Stuff to Find Things Wei-Cheng Su Motivation 2 Leverage contextual information to enhance detection Some context objects are non-rigid and are more naturally classified
More informationStrategies for simulating pedestrian navigation with multiple reinforcement learning agents
Strategies for simulating pedestrian navigation with multiple reinforcement learning agents Francisco Martinez-Gil, Miguel Lozano, Fernando Ferna ndez Presented by: Daniel Geschwender 9/29/2016 1 Overview
More informationMonte Carlo MCMC: Efficient Inference by Sampling Factors
University of Massachusetts Amherst From the SelectedWorks of Andrew McCallum 2012 Monte Carlo MCMC: Efficient Inference by Sampling Factors Sameer Singh Michael Wick Andrew McCallum, University of Massachusetts
More informationECLT 5810 Clustering
ECLT 5810 Clustering What is Cluster Analysis? Cluster: a collection of data objects Similar to one another within the same cluster Dissimilar to the objects in other clusters Cluster analysis Grouping
More informationLatent Variable Models for Structured Prediction and Content-Based Retrieval
Latent Variable Models for Structured Prediction and Content-Based Retrieval Ariadna Quattoni Universitat Politècnica de Catalunya Joint work with Borja Balle, Xavier Carreras, Adrià Recasens, Antonio
More informationAccelerating Markov Random Field Inference Using Molecular Optical Gibbs Sampling Units
Accelerating Markov Random Field Inference Using Molecular Optical Gibbs Sampling Units Siyang Wang, Xiangyu Zhang, Yuxuan Li, Ramin Bashizade, Song Yang, Chris Dwyer, Alvin Lebeck Duke University Probabilistic
More informationMeasuring and Reducing Observational Latency when Recognizing Actions
Measuring and Reducing Observational Latency when Recognizing Actions Syed Z. Masood Chris Ellis Adarsh Nagaraja Marshall F. Tappen Joseph J. LaViola Jr. University of Central Florida Orlando, Florida
More informationEstimating Missing Attribute Values Using Dynamically-Ordered Attribute Trees
Estimating Missing Attribute Values Using Dynamically-Ordered Attribute Trees Jing Wang Computer Science Department, The University of Iowa jing-wang-1@uiowa.edu W. Nick Street Management Sciences Department,
More informationDynamic Bayesian network (DBN)
Readings: K&F: 18.1, 18.2, 18.3, 18.4 ynamic Bayesian Networks Beyond 10708 Graphical Models 10708 Carlos Guestrin Carnegie Mellon University ecember 1 st, 2006 1 ynamic Bayesian network (BN) HMM defined
More informationSTRUCTURAL EDGE LEARNING FOR 3-D RECONSTRUCTION FROM A SINGLE STILL IMAGE. Nan Hu. Stanford University Electrical Engineering
STRUCTURAL EDGE LEARNING FOR 3-D RECONSTRUCTION FROM A SINGLE STILL IMAGE Nan Hu Stanford University Electrical Engineering nanhu@stanford.edu ABSTRACT Learning 3-D scene structure from a single still
More informationGraph-based Techniques for Searching Large-Scale Noisy Multimedia Data
Graph-based Techniques for Searching Large-Scale Noisy Multimedia Data Shih-Fu Chang Department of Electrical Engineering Department of Computer Science Columbia University Joint work with Jun Wang (IBM),
More informationFirst-Person Animal Activity Recognition from Egocentric Videos
First-Person Animal Activity Recognition from Egocentric Videos Yumi Iwashita Asamichi Takamine Ryo Kurazume School of Information Science and Electrical Engineering Kyushu University, Fukuoka, Japan yumi@ieee.org
More informationPackage CRF. February 1, 2017
Version 0.3-14 Title Conditional Random Fields Package CRF February 1, 2017 Implements modeling and computational tools for conditional random fields (CRF) model as well as other probabilistic undirected
More informationHandwritten Word Recognition using Conditional Random Fields
Handwritten Word Recognition using Conditional Random Fields Shravya Shetty Harish Srinivasan Sargur Srihari Center of Excellence for Document Analysis and Recognition (CEDAR) Department of Computer Science
More informationLocal Features and Kernels for Classifcation of Texture and Object Categories: A Comprehensive Study
Local Features and Kernels for Classifcation of Texture and Object Categories: A Comprehensive Study J. Zhang 1 M. Marszałek 1 S. Lazebnik 2 C. Schmid 1 1 INRIA Rhône-Alpes, LEAR - GRAVIR Montbonnot, France
More informationComputer Vision. Exercise Session 10 Image Categorization
Computer Vision Exercise Session 10 Image Categorization Object Categorization Task Description Given a small number of training images of a category, recognize a-priori unknown instances of that category
More informationCombining Top-down and Bottom-up Segmentation
Combining Top-down and Bottom-up Segmentation Authors: Eran Borenstein, Eitan Sharon, Shimon Ullman Presenter: Collin McCarthy Introduction Goal Separate object from background Problems Inaccuracies Top-down
More informationProbabilistic Structured-Output Perceptron: An Effective Probabilistic Method for Structured NLP Tasks
Probabilistic Structured-Output Perceptron: An Effective Probabilistic Method for Structured NLP Tasks Xu Sun MOE Key Laboratory of Computational Linguistics, Peking University Abstract Many structured
More informationBeyond Actions: Discriminative Models for Contextual Group Activities
Beyond Actions: Discriminative Models for Contextual Group Activities Tian Lan School of Computing Science Simon Fraser University tla58@sfu.ca Weilong Yang School of Computing Science Simon Fraser University
More informationLearning Deep Structured Models for Semantic Segmentation. Guosheng Lin
Learning Deep Structured Models for Semantic Segmentation Guosheng Lin Semantic Segmentation Outline Exploring Context with Deep Structured Models Guosheng Lin, Chunhua Shen, Ian Reid, Anton van dan Hengel;
More informationProbabilistic Cascade Random Fields for Man-Made Structure Detection
Probabilistic Cascade Random Fields for Man-Made Structure Detection Songfeng Zheng Department of Mathematics Missouri State University, Springfield, MO 65897, USA SongfengZheng@MissouriState.edu Abstract.
More informationAutomatic Gait Recognition. - Karthik Sridharan
Automatic Gait Recognition - Karthik Sridharan Gait as a Biometric Gait A person s manner of walking Webster Definition It is a non-contact, unobtrusive, perceivable at a distance and hard to disguise
More informationIntroduction to Trajectory Clustering. By YONGLI ZHANG
Introduction to Trajectory Clustering By YONGLI ZHANG Outline 1. Problem Definition 2. Clustering Methods for Trajectory data 3. Model-based Trajectory Clustering 4. Applications 5. Conclusions 1 Problem
More informationExtracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Lin Liao Dieter Fox Henry Kautz Department of Computer Science & Engineering University of Washington Seattle,
More informationActivity Recognition from Physiological Data using Conditional Random Fields
Activity Recognition from Physiological Data using Conditional Random Fields Hai Leong Chieu 1, Wee Sun Lee 2, Leslie Pack Kaelbling 3 1 Singapore-IT Alliance, National University of Singapore 2 Department
More informationPARALLEL SELECTIVE SAMPLING USING RELEVANCE VECTOR MACHINE FOR IMBALANCE DATA M. Athitya Kumaraguru 1, Viji Vinod 2, N.
Volume 117 No. 20 2017, 873-879 ISSN: 1311-8080 (printed version); ISSN: 1314-3395 (on-line version) url: http://www.ijpam.eu ijpam.eu PARALLEL SELECTIVE SAMPLING USING RELEVANCE VECTOR MACHINE FOR IMBALANCE
More informationLecture 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 informationRobustifying the Flock of Trackers
1-Feb-11 Matas, Vojir : Robustifying the Flock of Trackers 1 Robustifying the Flock of Trackers Tomáš Vojíř and Jiří Matas {matas, vojirtom}@cmp.felk.cvut.cz Department of Cybernetics, Faculty of Electrical
More information