WILLOW Research

	Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning CVPR 2023		Assembly Planning from Observations under Physical Constraints IROS 2022
	Zero-Shot Video Question Answering via Frozen Bidirectional Language Models NeurIPS 2022		Collision Detection Accelerated: An Optimization Perspective RSS 2022
	TubeDETR: Spatio-Temporal Video Grounding with Transformers CVPR 2022		Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation CVPR 2022
	Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos CVPR 2022		Large-Scale Unsupervised Object Discovery NeurIPS 2021
	History Aware Multimodal Transformer for Vision-and-Language Navigation NeurIPS 2021		CCVS: Context-aware Controllable Video Synthesis NeurIPS 2021
	Just Ask: Learning to Answer Questions from Millions of Narrated Videos ICCV 2021		Goal-Conditioned Reinforcement Learning with Imagined Subgoals ICML 2021
	Learning to combine primitive skills: A step towards versatile robotic manipulation ICRA 2020		CosyPose: Consistent multi-view multi-object 6D pose estimation ECCV 2020
	Learning Actionness via Long-range Temporal Order Verification ECCV 2020		Learning to Augment Synthetic Images for Sim2Real Policy Transfer IROS 2019
	Estimating 3D Motion and Forces of Person-Object Interactions from Monocular Video CVPR 2019		Cross-task weakly supervised learning from instructional videos CVPR 2019
	D2-Net: A Trainable CNN for Joint Detection and Description of Local Features CVPR 2019		SFNet: Learning Object-aware Semantic Flow CVPR 2019
	Learning joint reconstruction of hands and manipulated objects CVPR 2019		Neighbourhood Consensus Networks NeurIPS 2018
	A flexible model for training action localization with varying levels of supervision NeurIPS 2018		BodyNet: Volumetric Inference of 3D Human Body Shapes ECCV 2018
	End-to-end weakly-supervised semantic alignment CVPR 2018		Long-term Temporal Convolutions for Action Recognition PAMI 2018
	Joint Discovery of Object States and Manipulation Actions ICCV 2017		GANs for Biological Image Synthesis ICCV 2017
	Learning from Video and Text via Large-Scale Discriminative Clustering ICCV 2017		Weakly-supervised learning of visual relations ICCV 2017
	SCNet: Learning Semantic Correspondence ICCV 2017		Convolutional Neural Network Architecture for Geometric Matching CVPR 2017
	Learning from Synthetic Humans CVPR 2017		ContextLocNet: Context-aware Deep Network Models for Weakly Supervised Localization ECCV 2016
	Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding ECCV 2016		Thin-Slicing for Pose: Learning to Understand Pose without Explicit Pose Estimation CVPR 2016
	NetVLAD: CNN Architecture for Weakly Supervised Place Recognition CVPR 2016		Instance-level Video Segmentation from Object Tracks CVPR 2016
	Unsupervised Learning from Narrated Instruction Videos CVPR 2016		Proposal Flow CVPR 2016
	Learning Dictionary of Discriminative Part Detectors for Image Categorization and Cosegmentation IJCV 2016		Unsupervised Object Discovery and Tracking in Video Collections ICCV 2015
	Context-aware CNNs for Person Head Detection ICCV 2015		P-CNN: Pose-based CNN Features for Action Recognition ICCV 2015
	Is object localization for free? Weakly Supervised Object Recognition with Convolutional Neural Networks CVPR 2015		Unsupervised Object Discovery and Localization in the Wild CVPR 2015
	24/7 Place Recognition by view Synthesis CVPR 2015		The SD Filter: Robust Image Filtering Using Joint Static and Dynamic Guidance PAMI 2017, CVPR 2015
	Painting-to-3D Model Alignment Via Discriminative Visual Elements TOG 2014		Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks CVPR 2014
	Efficient Feature Extraction, Encoding and Classification for Action Recognition CVPR 2014		Seeing 3D chairs: Exemplar Part-based 2D-3D Alignment Using a Large Dataset of CAD Models CVPR 2014
	Learning Graphs to Match ICCV 2013		Finding Actors and Actions in Movies ICCV 2013
	Pose Estimation and Segmentation of People in 3D Movies ICCV 2013		Scene Semantics from Long-term Observation of People ECCV 2012
	People Watching: Human Actions as a Cue for Single-View Geometry ECCV 2012		Track to the Future: Spatio-temporal Video Segmentation with Long-range Motion Cues CVPR 2011
	Automatic Alignment of Paintings and Photographs Depicting a 3D Scene 3DRRW-ICCV 2011		Data-driven Crowd Analysis in Videos ICCV 2011
	Density-aware person detection and tracking in crowds ICCV 2011		Non-uniform Deblurring for Shaken Images IJCV 2012, CVPR 2010
	Deblurring Shaken and Partially Saturated Images CPCVW-ICCV 2011		Avoding confusing features in place recognition ECCV 2010
	Facial Attribute Classification in Video ECCV 2010		Human Action Classification in Still Images BMVC 2010
	Patch-based Multi-view Stereo Software PAMI 2010, CVPR 2007		What is a Camera? CVPR 2009
	Dense 3D Motion Capture for Human Faces CVPR 2009		Internet-based Inpainting BMVC 2009

Activity Reports

Activity Report 2016
Activity Report 2013	Activity Report 2014	Activity Report 2015
Activity Report 2010	Activity Report 2011	Activity Report 2012
Activity Report 2007	Activity Report 2008	Activity Report 2009