Showing 1–20 of 32 results
/ Date/ Name
Dec 22, 2017On the Integration of Optical Flow and Action RecognitionMar 12, 2016Optical Flow with Semantic Segmentation and Localized LayersJun 9, 2022Learn2Augment: Learning to Composite Videos for Data Augmentation in Action RecognitionOct 10, 2022An Action Is Worth Multiple Words: Handling Ambiguity in Action RecognitionJul 19, 2019Only Time Can Tell: Discovering Temporal Data for Temporal ModelingOct 3, 2025Mask2IV: Interaction-Centric Video Generation via Mask TrajectoriesJan 11, 2019DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action RecognitionApr 5, 2021Adaptive Prototype Learning and Allocation for Few-Shot SegmentationJul 27, 2021A New Split for Evaluating True Zero-Shot Action RecognitionJan 18, 2021CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action RecognitionDec 19, 2020SMART Frame Selection for Action RecognitionSep 30, 2022A Closer Look at Temporal Ordering in the Segmentation of Instructional VideosOct 10, 2023Watt For What: Rethinking Deep Learning's Energy-Performance RelationshipMay 13, 2024Coarse or Fine? Recognising Action End States without LabelsNov 27, 2023Efficient Pre-training for Localized Instruction Generation of VideosNov 20, 2024Principles of Visual Tokens for Efficient Video UnderstandingMay 27, 2025Predicting Implicit Arguments in Procedural Video InstructionsFeb 16, 2026It's a Matter of Time: Three Lessons on Long-Term Motion for PerceptionMay 3, 2017Optical Flow in Mostly Rigid ScenesAug 19, 2024Learning Precise Affordances from Egocentric Videos for Robotic Manipulation