Computer Vision Reading Group

To subscribe to the mailing list for talk announcements, send a message to with the words subscribe cvrg-l in the body.

We will be restarting the reading group for the summer term after May 1, 2022

A list of upcoming papers can be found below. To be added to the schedule contact Frank (

Upcoming presentations

Date Presenter Paper or topic

Finished presentations, 2022

Date Presenter Paper or topic
Apr. 12

Embedding Arithmetic for Text-driven Image Transformation [link]
Apr. 5

Block-NeRF Scalable Large Scene Neural View Synthesis [link]
On the Continuity of Rotation Representations in Neural Networks [link]
Mar. 15

GAN-Supervised Dense Visual Alignment [link]
Feb. 15

Instant Neural Graphics Primitives with a Multiresolution Hash Encoding [link]
BANMo: Building Animatable 3D Neural Models from Many Casual Videos [link]
Feb. 8
Daniel Rebain
Ling Mei

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations [link]
Resolution-aware Knowledge Distillation for Efficient Inference [link]
Feb. 1

gDNA: Towards Generative Detailed Neural Avatars [link]
Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects [link]

Finished presentations, 2021

Date Presenter Paper or topic
Feb. 1

gDNA: Towards Generative Detailed Neural Avatars [link]
Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects [link]
Nov. 24
Geoff Woollard

ReFormer: The Relational Transformer for Image Captioning [link]
CNNs on surfaces using rotation-equivariant features [link]
Oct. 27

Dynamic View Synthesis from Dynamic Monocular Video [link]
Understanding Object Dynamics for Interactive Image-to-Video Synthesis [link]
Oct. 20
Weiwei Sun

The Functional Correspondence Problem [link]
Oct. 6
Video Generation
Playable Video Generation [link]
Oct. 13

Efficiently Identifying Task Groupings for Multi-Task Learning [link]
The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning [link]
Sept. 29
Context-aware Scene Graph Generation with Seq2Seq Transformers [link]
Sept. 22

PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction [link]
Aug. 17
Daniel Ajisafe
Human Pose
Reconstructing 3D Human Pose by Watching Humans in the Mirror [link]
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis [link]
Aug. 10


Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks [link]
End-to-end Learned, Optically Coded Super-resolution SPAD Camera [link]
Aug. 3


Skip-Convolutions for Efficient Video Processing [link]
MLP-Mixer: An all-MLP Architecture for Vision [link]
Jul. 27


Unsupervised Learning of Visual 3D Keypoints for Control [link]
Self-supervised Geometric Perception [link]
Jul. 20


Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood Estimation [link]
Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image [link]
Jul. 13
Wei Jiang

Editable Free-viewpoint Video Using a Layered Neural Representation [link]
Jul. 6


Neural Lumigraph Rendering [link]
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video [link]
Jun. 29
Kacper Kania


Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering [link]
SFV: Reinforcement Learning of Physical Skills from Videos [link]
Apr. 6
VisualCOMET: Reasoning about the Dynamic Context of a Still Image [link]
Mar. 30
How Powerful Are Randomly Initialized Pointcloud Set Functions? [link]
Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization [link]
Mar. 23
One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing [link]
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance [link]
Mar. 9

ACFNet: Attentional Class Feature Network for Semantic Segmentation [link]
Object Detection
Deformable DETR: Deformable Transformers for End-to-End Object Detection [link]
Mar. 2
Rethinking Attention with Performers [link]
Feb. 23

Graph Neural Network
Temporal Graph Networks for Deep Learning on Dynamic Graphs [link]
Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets [link]
Feb. 9
Graph Neural Network
Graph-based global reasoning networks [link]
Feb. 2
Temporal Action Detection with Multi-level Supervision [link]
Jan. 26
Learning Representations that Support Extrapolation [link]

Finished presentations, 2020

Date Presenter Paper or topic
Dec. 18

3D Vision
Self-Calibration Supported Robust Projective Structure-from-Motion [link]
Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases [link]
Dec. 11
Daniel Rebain
Wei Jiang
3D Vision
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections [link]
Crowdsampling the Plenoptic Function [link]
Dec. 4
3D Representation Learning
Leveraging 2D Data to Learn Textured 3D Mesh Generation [link]
Object-Centric Multi-View Aggregation [link]
Nov. 27
3D Representation Learning
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding [link]
SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification [link]
Nov. 20
We Have So Much In Common: Modeling Semantic Relational Set Abstractions in Videos [link]
Oct. 30
Graph Neural Network
Dynamic Graph Message Passing Networks [link]
GPS-Net: Graph Property Sensing Network for Scene Graph Generation [link]
Oct. 23
Object Detection
Frustratingly Simple Few-Shot Object Detection [link]
End-to-End Object Detection with Transformers [link]
Oct. 16
Generative Model Applications
Semantic Pyramid for Image Generation [link]
GeLaTO: Generative Latent Textured Objects [link]
Oct. 9

3D Vision
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains [link]
Human Pose
Long-term Human Motion Prediction with Scene Context [link]
Oct. 2
Vision & Sound
Music Gesture for Visual Sound Separation [link]
Telling Left from Right: Learning Spatial Correspondence of Sight and Sound [link]
Sep. 25
PointRend: Image Segmentation as Rendering [link]
Mar. 11
GAN & 3D
Semantic Image Synthesis with Spatially-Adaptive Normalization [link]
Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations [link]
Feb. 12
Multimodality Applications
Listen to Look: Action Recognition by Previewing Audio [link]
Language2Pose: Natural Language Grounded Pose Forecasting [link]
Feb. 5
Video Action Recognition
Action Genome: Actions as Composition of Spatio-temporal Scene Graphs [link]
Jan. 29
Vision & Language
Adaptively Aligned Image Captioning via Adaptive Attention Time [link]
Jan. 22
Vision & Language
Heterogeneous Graph Learning for Visual Commonsense Reasoning [link]
Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries [link]

Finished presentations, 2019

Date Presenter Paper or topic
Dec. 5 Polina

Multi-Object Representation Learning with Iterative Variational Inference [link]
Generative Model Applications
Lifelong GAN: Continual Learning for Conditional Image Generation [link]
Nov. 29
Invertible Residual Networks [link]
Non-local Neural Network [link]
Nov. 21
Reinforcement Learning / Learning
Learning to Paint With Model-based Deep Reinforcement Learning [link]
Deep Equilibrium Models [link]
Oct. 24

3D Human Pose
3D Human Pose Estimation in Video with Temporal Convolutions and Semi-supervised Training [link]
Generative Model Applications
Neural Re-Simulation for Generating Bounces in Single Images [link]
Oct. 17
Graph Neural Network
Modeling Relational Data with Graph Convolutional Networks [link]
Understanding Attention and Generalization in Graph Neural Networks [link]
Oct. 10
Vision & Language
From Recognition to Cognition: Visual Commonsense Reasoning [link]
Task-Driven Modular Networks for Zero-Shot Compositional Learning [link]
Oct. 3
Vision & Language
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks [link]
Video Representation Learning by Dense Predictive Coding [link]
Sep. 26
Vision & Graphics
Fashion++: Minimal Edits for Outfit Improvement [link]
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization [link]
Sep. 19
Flow-based Generative Models
Graph Normalizing Flows [link]
Glow: Generative Flow with Invertible 1x1 Convolutions [link]
Apr. 16

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks [link]
Unsupervised Learning
Unsupervised Learning via Meta-Learning [link]
Apr. 9
A Style-Based Generator Architecture for Generative Adversarial Networks [link]
Apr. 2

An Overview of Multi-Task Learning in Deep Neural Networks [link]
Panoptic Feature Pyramid Networks [link]
Mar. 26

Lifetime Learning
Efficient Lifelong Learning with A-GEM [link]
Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks [link]
Mar. 12
Lifetime Learning
End-to-End Incremental Learning [link]
Memory Aware Synapses: Learning What (not) to Forget [link]
Feb. 26
Generative Models
Probabilistic Neural Programmed Networks for Scene Generation [link]
Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects [link]
Feb. 5 Alireza Neural Ordinary Differential Equations [link]
Jan. 15

Video Generative Models
Video-to-video Synthesis [link]
NN Optimization
Group Normalization [link]

Finished presentations, 2018

Date Presenter Paper or topic
Nov. 22

Unsupervised GANs
Dense Pose Transfer [link]
Video Generative Models
Everybody Dance Now [link]
Nov. 8
Unsupervised GANs
Diverse Image-to-Image Translation via Disentangled Representations [link]
GANimation: Anatomically-aware Facial Animation from a Single Image [link]
Nov. 1
Adversarial Autoencoders [link]
Oct. 25
Reasoning with Interpretability
Explainable Neural Computation via Stack Neural Module Networks [link]
Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning [link]
Oct. 18
Overview of Bias in NN
Relational Inductive Biases, Deep Learning, and Graph Networks [link]
Oct. 11
Scene Understanding & Reasoning
Compositional Neural Networks for Machine Reasoning [link]
Iterative Visual Reasoning Beyond Convolution [link]
Oct. 4
Scene Understanding & Reasoning
Detecting Objects by Transferring Common-sense Knowledge [link]
Graph R-CNN for Scene Graph Generation [link]
Apr. 6 Candice What have we learned from deep representations for action recognition? [link]
Mar. 23 Gursimran A Simple Neural Network Module for Relational Reasoning [link]
Mar. 2 Polina Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis [link]
Feb. 16 Suhail AttnGAN [link]
Generative Adversarial Text to Image Synthesis [link]
Feb. 9 Borna Mask R-CNN [link]
Feb. 2 Bicheng Teaching Machines to Describe Images via Natural Language Feedback [link]
Jan. 26 Alireza Is it hard to say I don't know?
Jan. 19 Bo Inferring and Executing Programs for Visual Reasoning [link]

Finished presentations, 2017

Date Presenter Paper or topic
July 11, 2017 Jianhui Chen Shan Su etal. Social Behavior Prediction from First Person Videos , [pdf]
July 4, 2017 Julieta Martinez Meire Fortunato etal. Noisy Networks for Exploration , [pdf]
June 27, 2017 Rayat Hossain Kaiming He etal. Mask R-CNN , [pdf]
April 13, 2017 Julieta Martinez Rudy Bunel etal. Learning to superoptimize programs , [pdf]
April 7, 2017 Jimmy Chen Shenlong Wang etal. The Global Patch Collider , [pdf]
Match 10, 2017 Jimmy Chen Jimmy's thesis proposal
Match 3, 2017 Vision group Demos on Grad Visit Day
February 24, 2017 Lei Xiao Proximal Learning for Computational Imaging
February 17, 2017 Moumita Roy, Keyu Lu and Jimmy Chen A tutorial of Tensorflow, MatConvNet and Caffe
February 3, 2017 Jimmy Chen The-Anh Pham. Pair-wisely optimized clustering tree for feature indexing , [pdf]
February 6, 2017 Fred Tung Fred's PhD thesis defense
February 6, 2017 John K. Tsotsos Attention is More Important for AI Than You Think
January 20, 2017 Julieta Martinez Francesc Moreno-Noguer 3D Human Pose Estimation from a Single Image via Distance Matrix Regression, unpublished [pdf]
January 13, 2017 Jimmy Chen Lakshminarayanan etal. Mondrian Forests: Efficient Online Random Forests, NIPS 2014 [pdf]

Finished presentations, 2016

Date Presenter Paper or topic
December 14, 2016 Fred Tung ACCV 2016 recap. [ACCV 2016]
December 7, 2016 Rayat Imtiaz Bugar Tekin etal. Structured Prediction of 3D Human Pose with Deep Neural Networks , BMVC 2016 [pdf]
November 23, 2016 Moumita Roy Vignesh Ramanathan etal. Detecting events and key actors in multi-person videos , CVPR 2016 [pdf]
November 14, 2016 Fred Tung Fred Tung and Jim Little: SSP: Supervised Sparse Projections for large-scale retrieval in high dimensions , ACCV 2016 [pdf]
October 26, 2016 Jim Little ECCV 2016 recap [ECCV2016]
October 5, 2016 Fred Tung and Lili Meng BMVC 2016 recap
September 28, 2016 Jimmy Chen Du Tran et al: Learning Spatiotemporal Features with 3D Convolutional Networks , ICCV 2015 [pdf]
September 14, 2016 Moumita Roy Zhiwei Deng et al: Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition , CVPR 2016 [pdf]
August 17, 2016 Fred Tung Fred Tung and Jim Little, Factorized binary codes for large-scale nearest neighbor search , to appear BMVC 2016 [pdf]
August 10, 2016 Rayat Imtiaz Federica Bogo et al: Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image, from ECCV 16 [pdf]
August 3, 2016 Micha Livne Performance capture
July 20, 2016 Ankur Gupta Ashesh Jain et al: Structural-RNN: Deep Learning on Spatio-Temporal Graphs [pdf]
July 13, 2016 Many Greg Mori and his students visited cvrg to talk about their ongoing and future research
July 11, 2016 Ankur Gupta, Jimmy Chen and Julieta Martinez A recap on CVPR 16
July 6, 2016 Julieta Martinez Relja Arandjelovic, Petr Gronat, Akihiko Torii, Tomas Pajdla, Josef Sivic NetVLAD: CNN Architecture for Weakly Supervised Place Recognition, from CVPR 16 [pdf]
June 22, 2016 Jimmy Chen Jianhui Chen, Hoang M. Le, Peter Carr, Yisong Yue, James J. Little Learning Online Smooth Predictions for Realtime Camera Planning using Recurrent Decision Trees, from CVPR 16 [pdf]
June 21, 2016 Richard Wildes A Tale of Two Reference Frames
June 15, 2016 Ankur Gupta Ankur rehearsed his PhD thesis defense
June 1, 2016 Lili Meng Eric Brachmann, Frank Michel, Alexander Krull, Michael Ying Yang, Stefan Gumhold, and Carsten Rother Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image, to appear at CVPR 2016 [pdf]
May 10, 2016 Moumita Roy Aaron van den Oord, Nal Kalchbrenner, Koray Kavukcuoglu Pixel Recurrent Neural Networks, from ICML 2016 [pdf]
May 10, 2016 Rayat Imtiaz Xiaowei Zhou, Menglong Zhu, Spyridon Leonardos, Kosta Derpanis, Kostas Daniilidis Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video, to appear at CVPR 2016 [pdf]
May 4, 2016 Julieta Martinez Deepak Pathak, Phillip Krähenbühl, Jeff Donahue, Trevor Darrell, Alexei A. Efros Context Encoders: Feature Learning by Inpainting, to appear at CVPR 2016 [pdf]
April 20, 2016 Julieta Martinez Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jifeng Dai, & Jian Sun: Deep residual learning for image recognition, to appear at CVPR 2016 [pdf]
April 6, 2016 Jimmy Chen Valentin et al.: Exploiting Uncertainty in Regression Forests for Accurate Camera Relocalization, from CVPR 2015 [pdf]
March 23, 2016 Fred Tung Shuran Song and Jianxiong Xiao: Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images, to appear at CVPR 2016 [pdf]
March 16, 2016 Ankur Gupta A report trip from WACV 2016.
February 9, 2016 Ankur Gupta Katerina Fragkiadaki, Sergey Levine, Panna Felsen, Jitendra Malik: Recurrent Network Models for Human Dynamics, from ICCV 2015 [pdf]
January 27, 2016 Anahita Shojaei Limin Wang, Yu Qiao and Xiaoou Tang: Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors, from CVPR 2015 [pdf]
January 27, 2016 Jimmy Chen Alex Kendall, Matthew Grimes and Roberto Cipolla: PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization, from ICCV 2015 [pdf]
January 20, 2016 Julieta Martinez Emily L. Denton, Soumith Chintala, Arthur Szlam, Rob Fergus: Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks, from NIPS 2015 [pdf]
January 13, 2016 Rayat Imtiaz Lawrence Zitnick and Devi Parikh: Bringing Semantics into Focus using Visual Abstraction, from CVPR 2013 [pdf]

Finished presentations, 2015

Date Presenter Paper or topic
December 11, 2015 -- We watched the CVPR 15 plenary talk by Yann LeCun: What is wrong with deep learning? [techtalk].
November 27, 2015 Julieta Martinez Artem Babenko and Victor Lempitsky: Aggregating deep convolutional features for image retrieval., from ICCV 2015 [pdf]
November 20, 2015 Alireza Shafaei A tutorial / literature review on depth estimation from rgb.
November 13, 2015 Fred Tung Hang Su, Subhransu Maji, Evangelos Kalogerakis, and Erik Learned-Miller: Multi-view convolutional neural networks for 3D shape recognition, from ICCV 2015 [pdf]
October 30, 2015 Joris Clement A talk on his research as an intern in the vision lab related to large-scale retrieval.
October 19, 2015 Alireza Shafaei Real-time Human Motion Capture with Depth Sensors, as part of his MSc thesis presentation.
October 16, 2015 Jimmy Chen Camera Planning for Soccer Games, as part of his RPE.
October 9, 2015 Kevin Woo Bogo F. et al.: Detailed Full-Body Reconstructions of Moving People from Monocular RGB-D Sequences, from ICCV 2015 [html].
October 2, 2015 Julieta Martinez Zheng S. et al.: Conditional Random Fields as Recurrent Neural Networks, from ICCV 2015 [html].
September 24, 2015 Deva Ramanan Distinguished Lecture Series: Understanding Visual Appearances in the Long-tail [html][youtube].
August 20, 27 & Sept 3, 2015 Various We are attending the seminar on probabilistic graphical models organized by the machine learning reading group.
August 15, 2015 Fred Tung A. Gonzalez-Garcia, A. Vezhnevets, V. Ferrari. An active search strategy for efficient object class detection, from CVPR 2015 [pdf].
August 6, 2015 John He Retrieval of human motion with flexible alignment.
July 30, 2015 Julieta Martinez A whirlwind tour on vector compression for large-scale computer vision applications.
July 23, 2015 Olga Russakovsky Scaling up Object Detection.
July 16, 2015 Lili Meng Richard A. Newcombe, Steven J. Lovegrove and Andrew J. Davison. DTAM: Dense Tracking and Mapping in Real-Time, from ICCV 2011. [pdf]
July 9, 2015 Jimmy Chen Guzmán-Rivera et al. Multi-Output Learning for Camera Relocalization, from CVPR 14 [pdf]
July 2, 2015 Alireza Shafaei Ho Yub Jung, Soochahn Lee, Yong Seok Heo and Il Dong Yun. Random Tree Walk toward Instantaneous 3D Human Pose Estimation, from CVPR 15. [pdf]
June 25, 2015 Julieta Martinez Ijaz Akhter and Michael J. Black. Pose-Conditioned Joint Angle Limits for 3D Human Pose Reconstruction, from CVPR 2015. [pdf]
June 18, 2015 Jim Little A report on his trip to CVPR 2015.
June 4, 2015 Ankur Gupta Meyer et al. Phase-Based Frame Interpolation for Video, from CVPR 2015 [pdf]
March 20, 2015 Fred Tung Abhijit Kundu, Yin Li, Frank Daellert, Fuxin Li and James M. Rehg. Joint Semantic Segmentation and 3D Reconstruction from Monocular Video, from ECCV 2014. [pdf]
March 13, 2015 Ankur Gupta Matthew M. Loper and Michael J. Black. OpenDR: An Approximate Differentiable Renderer, from ECCV 2014. [pdf]
February 27, 2015 Julieta Martinez Katerina Fragkiadaki, Marta Salas, Pablo Arbelaez and Jitendra Malik. Grouping-Based Low-Rank Trajectory Completion and 3D Reconstruction, from NIPS 2014. [pdf]
February 13, 2015 Jimmy Chen Dubská, M., Sochor, J., & Herout, A. Automatic Camera Calibration for Traffic Understanding, from BMVC 2014 [pdf].
February 6, 2015 Victor Gan Rodrigo Benenson, Mohamed Omran, Jan Hosang and Bernt Schiele. Ten Years of Pedestrian Detection, What Have We Learned? posted to arxiv on November last year [pdf].
January 30, 2015Ankur Gupta Mohsen Hejrati and Deva Ramanan. Analysis by Synthesis: 3D Object Recognition by Object Reconstruction, from CVPR 2014. [pdf]
January 23, 2015Alireza Shafaei Andrej Karpathy and Fei-Fei Li. Deep visual-semantic alignments for generating image descriptions. arXiv preprint arXiv:1412.2306 (2014). [arxiv]
January 16, 2015 Jimmy Chen & Fred Tung A recap on WACV 15.

Finished presentations, 2014

Date Presenter Paper or topic
Nov 20, 2014 Julieta Martinez Pickup, L.C., Pan, Z., Wei, D., Shih, Y., Zhang, C., Zisserman, A., Schölkopf, B. and Freeman, W.T. Seeing the Arrow of Time. [pdf]
Oct 30, 2014 Alireza Shafaei Kevin Matzen and Noah Snavely. Scene Chronology, from ECCV 2014 [pdf]
Oct 23, 2014 Jimmy Chen Sean Ryan Fanello, Cem Keskin, Pushmeet Kohli, Shahram Izadi, Jamie Shotton, Antonio Criminisi, Ugo Pattacini, Tim Paek. Learning Data-Dependent Convolutional Kernels, from CVPR 2014 [pdf]
Oct 16, 2014 Victor Gan Laurens van der Maaten. Barnes-Hut-SNE, from ICLR 2013 [pdf].
Oct 8, 2014 Alireza Shafaei Ross Girshick, Forrest Iandola, Trevor Darrell and Jitendra Malik. Deformable Part Models are Convolutional Neural Networks, from Arxiv a few weeks ago [pdf].
Oct 1, 2014 Julieta Martinez Shiry Ginosar, Daniel Haas, Timothy Brown, and Jitendra Malik. Detecting People in Cubist Art. [arxiv], and Crowley, E. J., Zisserman, A. The State of the Art: Object Retrieval in Paintings using Discriminative Regions [pdf] from BMVC 2014.
Sept 24, 2014 Fred Tung A trip report on ECCV 2014.
Sept 17, 2014 Alireza Shafaei Jia Deng, Nan Ding, Yangqing Jia, Andrea Frome, Kevin Murphy, Samy Bengio, Yuan Li, Hartmut Neven, Hartwig Adam. Large-Scale Object Classification using Label Relation Graphs, from ECCV 2014. [external link].
July 22, 2014 Ankur GuptaChun-Hao Huang, Edmond Boyer, Nassir Navab, Slobodan Ilic, Human Shape and Pose Tracking Using Keyframes, CVPR 2014. [external link].
July 15, 2014 Alireza ShafaeiJonathan Tompson, Arjun Jain, Yann LeCun, Christoph Bregler, Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation, ArXiv preprint.[external link].
June 10, 2014 Neil TraftHenriques, J. F., Caseiro, R., Martins, P., & Batista, J, Exploiting the circulant structure of tracking-by-detection with kernels, ECCV 2012. [external link].
May 27, 2014 Alireza Shafaei Hamed Pirsiavash, Deva Ramanan, Parsing videos of actions with segmental grammars, CVPR 2014. [external link].
May 20, 2014 Ankur Gupta Andreas Lehrmann, Peter Gehler, Sebastian Nowozin, Efficient Nonlinear Markov Models for Human Motion, CVPR 2014. [external link].
May 12, 2014 Alireza Shafaei Anoop Cherian, Julien Mairal, Karteek Alahari, Cordelia Schmid, Mixing Body-Part Sequences for Human Pose Estimation, CVPR 2014. [external link].
April 28, 2014 Julieta Martinez Mohammad Norouzi Ali Punjani David J. Fleet, Fast Search in Hamming Space with Multi-Index Hashing, CVPR 2012. [external link].
April 10, 2014 Ankur GuptaRyan Tokola, Wongun Choi, Silvio Savarese, Breaking the chain: liberation from the temporal Markov assumption for tracking human poses, ICCV 2013. [external link].
March 24, 2014 Ankur GuptaAndreas Lehrmann, Peter V. Gehler, Sebastian Nowozin, A Non-parametric Bayesian Network Prior of Human Pose, ICCV 2013. [external link].
March 17, 2014 Julieta MartinezR Urtasun, T Darrell. Sparse probabilistic regression for activity-independent human pose inference. CVPR 2008. [external link].
Feb 03, 2014 Julieta MartinezE. Simo-Serra, A. Quattoni, C. Torras, and F. Moreno-Noguer. A Joint Model for 2D and 3D Pose Estimation from a Single Image. CVPR '13. [external link].
Jan 27, 2014 Jim LittleXinchao Wang, Vitaly Ablavsky, Horesh Ben Shitrit, and Pascal Fua. Take your Eyes off the Ball: Improving Ball-Tracking by Focusing on Team Play Computer Vision and Image Understanding (CVIU), Vol. 119, 2014. [external link].
Jan 20, 2014 Ankur GuptaDicle, C., Sznaier, M., & Camps, O. The Way They Move: Tracking Multiple Targets with Similar Appearance, from ICCV 2013. [external link].

Finished presentations, 2013

Date Presenter Paper or topic
Dec 06, 2013 Fred TungGuangnan Yey, Dong Liuy, Jun Wangz, and Shih-Fu Changy. Large Scale Video Hashing via Structure Learning. ICCV'13. [external link].
Nov 29, 2013 Ankur GuptaHueihan Jhuang, Juergen Gall, Silvia Zuffi, Cordelia Schmid, and Michael J. Black. Towards understanding action recognition. ICCV'13. [external link].
Nov 22, 2013 Julieta MartinezMatthijs Douze, Jerome Revaud, Cordelia Schmid and Herve Jegou. Stable hyper-pooling and query expansion for event detection. ICCV'13. [external link].
Nov 15, 2013 Anil MahmudAlldrin, N.G. and Kriegman, D. Toward Reconstructing Surfaces With Arbitrary Isotropic Reflectance : A Stratified Photometric Stereo Approach. ICCV'07. [external link].
Nov 08, 2013 Georgii OleinikovBen Sapp and Ben Taskar. MODEC: Multimodal Decomposable Models for Human Pose Estimation. CVPR'13. [external link].
Oct 18, 2013 Julieta MartinezHerve Jegou, Ondrej Chum. Negative evidences and co-occurrences in image retrieval: the benefit of PCA and whitening. ECCV'12. [external link].
Oct 11, 2013 Anil MahmudThoma Papadhimitri and Paolo Favaro. A New Perspective on Uncalibrated Photometric Stereo. CVPR'13. [external link]. Additional reading: Photometric stereo under a light source with arbitrary motion [link], Photometric stereo under perspective projection [link].
Sept 27, 2013 Ankur GuptaZhang, Z., Wang, C., Xiao, B., Zhou, W., Liu, S., & Shi, C. Cross-View Action Recognition via a Continuous Virtual Path. CVPR'13. [external link]
Sept 13, 2013 Julieta MartinezJrme Revaud, Matthijs Douze, Cordelia Schmid, Herv Jgou. Event Retrieval in Large Video Collections with Circulant Temporal Encoding. CVPR'13. [external link]
July 25, 2013 Julieta MartinezFragkiadaki F., Hu H. and Shi J. Pose from Flow and Flow from Pose. CVPR'13. [external link]
July 18, 2013 Georgii OleinikovYicong Tian, Rahul Sukthankar, Mubarak Shah. Spatiotemporal Deformable Part Models for Action Detection, Computer Vision and Pattern Recognition (CVPR), Portland, Oregan, June 2013. [external link]
June 20, 2013 Georgii OleinikovL. Ladický, P.H.S. Torr, A. Zisserman. Human Pose Estimation using a Joint Pixel-wise and Part-wise Formulation. To appear at CVPR 2013. [external link]
June 13, 2013 Julieta MartinezArpit Jain, Abhinav Gupta, Mikel Rodriguez, Larry S. Davis Representing Videos using Mid-level Discriminative Patches. To appear at CVPR 2013. [external link]
June 06, 2013 Ankur GuptaChao-Yeh Chen and Kristen Grauman. Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots. To appear at CVPR 2013. [external link]
April 05, 2013 Ankur GuptaRaptis, M., Kokkinos, I., & Soatto, S. (2012). Discovering discriminative action parts from mid-level video representations. Presented at CVPR 2012. [external link]
March 15, 2013 Bob WoodhamHao-Yu Wu, Michael Rubinstein, Eugene Shih, John Guttag, Frédo Durand,& William T. Eulerian Video Magnification for Revealing Subtle Changes in the World. Presented at SIGGRAPH 2012. [external link]
March 08, 2013 Julieta MartinezHenriques, J. F., Caseiro, R., Martins, P., & Batista, J. Exploiting the Circulant Structure of Tracking-by-detection with Kernels. Presented at ECCV 2012. [external link]
Feb 08, 2013 Georgii OleinikovCamps, O. I., & Sznaier, M. Cross-view activity recognition using Hankelets. IEEE Conference on Computer Vision and Pattern Recognition, 1362-1369, 2012. [external link]
Feb 01, 2013 Jim LittleVincent Delaitre, David F. Fouhey, Ivan Laptev, Josef Sivic, Abhinav Gupta, Alexei Efros. Scene semantics from long-term observation of people. In Proc. 12th European Conference on Computer Vision. 2012. [external link]
Jan 18, 2013 Georgii OleinikovH. Jhuang, T. Serre, L. Wolf, and T. Poggio. A biologically inspired system for action recognition. ICCV, pp. 1-8, 2007 [external link]
Jan 11, 2013 David MathesonChristian Leistner, Martin Godec, Samuel Schulter, Amir Saffari, Manuel Werlberger, and Horst Bischof Improving Classifiers with Unlabeled Weakly-Related Videos In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2011 [external link]

Finished presentations, 2012

Date Presenter Paper or topic
Dec 10, 2012 Junaed SattarFrançois Fleuret, Jérôme Berclaz, Richard Lengagne, Pascal Fua. Multicamera People Tracking with a Probabilistic Occupancy Map, PAMI, 2008. [paper link]
Dec 03, 2012 Ankur GuptaO. Kliper-Gross, Y. Gurovich, T. Hassner, and L. Wolf, Motion Interchange Patterns for Action Recognition in Unconstrained Videos, European Conference on Computer Vision (ECCV), Firenze, Italy, Oct 2012 [external link]
Nov 26, 2012 Jim LittleWongun Choi and Silvio Savarese, A Unified Framework for Multi-Target Tracking and Collective Activity Recognition, ECCV'12. [external link]
Nov 19, 2012 Masaki TakahasiBo Yang and Ram Nevatia, An Online Learned CRF Model for Multi-Target Tracking. In Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR), Providence, USA, Jun. 2012 [Paper link]
Nov 5, 2012 Ankur GuptaKevin Karsch, Ce Liu, Sing Bing Kang, Depth Extraction from Video Using Non-parametric Sampling, ECCV'12. [external link]
Oct 29, 2012 David MathesonZ. Kalal, J. Matas, and K. Mikolajczyk, P-N learning: Bootstrapping binary classifiers by structural constraints, Conference on Computer Vision and Pattern Recognition, 2010. [external link]
Oct 22, 2012 Masaki TakahasiHervé Jégou, Matthijs Douze, Cordelia Schmid, Patrick Pérez, Aggregating local descriptors into a compact image representation, IEEE Conference on Computer Vision & Pattern Recognition, 2010.[external link]