{"total":36,"rows":[{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2107.04932","title":"Aligning Correlation Information for Domain Adaptation in Action Recognition","created":"2021-07-11","cited_by_count":30,"area":null},{"id":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","cited_by_count":28,"area":null},{"id":"2210.12686","title":"Holistic Interaction Transformer Network for Action Detection","created":"2022-10-23","cited_by_count":28,"area":null},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2104.07461","title":"Action Segmentation with Mixed Temporal Domain Adaptation","created":"2021-04-15","cited_by_count":21,"area":null},{"id":"2205.13349","title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","created":"2022-05-26","cited_by_count":21,"area":null},{"id":"2111.01936","title":"Revisiting spatio-temporal layouts for compositional action recognition","created":"2021-11-02","cited_by_count":19,"area":null},{"id":"2204.03101","title":"Hierarchical Self-supervised Representation Learning for Movie Understanding","created":"2022-04-06","cited_by_count":19,"area":null},{"id":"2107.10771","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","created":"2021-07-22","cited_by_count":16,"area":null},{"id":"2103.10574","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","created":"2021-03-19","cited_by_count":12,"area":null},{"id":"2104.00646","title":"Motion Guided Attention Fusion to Recognize Interactions from Videos","created":"2021-04-01","cited_by_count":10,"area":null},{"id":"2206.01266","title":"Exponential Separations in Symmetric Neural Networks","created":"2022-06-02","cited_by_count":10,"area":null},{"id":"2106.13201","title":"DROID: Driver-centric Risk Object Identification","created":"2021-06-24","cited_by_count":9,"area":null},{"id":"2109.00522","title":"Conditional Extreme Value Theory for Open Set Video Domain Adaptation","created":"2021-09-01","cited_by_count":9,"area":null},{"id":"2104.12727","title":"2.5D Visual Relationship Detection","created":"2021-04-26","cited_by_count":7,"area":null},{"id":"2102.08065","title":"Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries","created":"2021-02-16","cited_by_count":6,"area":null},{"id":"2211.07501","title":"Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2106.08543","title":"Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2503.13707","title":"Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2204.04913","title":"Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2405.12789","title":"Anticipating Object State Changes in Long Procedural Videos","created":"2024-05-21","cited_by_count":2,"area":null},{"id":"2107.07154","title":"What and When to Look?: Temporal Span Proposal Network for Video Relation Detection","created":"2021-07-15","cited_by_count":1,"area":null},{"id":"2111.07370","title":"Co-segmentation Inspired Attention Module for Video-based Computer Vision Tasks","created":"2021-11-14","cited_by_count":1,"area":null},{"id":"2305.02673","title":"Modelling Spatio-Temporal Interactions For Compositional Action Recognition","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2307.12179","title":"Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs","created":"2023-07-22","cited_by_count":1,"area":null},{"id":"2402.17680","title":"MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2409.17356","title":"A vision-based framework for human behavior understanding in industrial assembly lines","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2206.06346","title":"Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2305.09539","title":"Learning Higher-order Object Interactions for Keypoint-based Video Understanding","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2310.02887","title":"A Grammatical Compositional Model for Video Action Detection","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2608.20690","title":"Identity-Aware Human-Object Interaction Motion Captioning","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}