{"total":13,"rows":[{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361,"area":null},{"id":"2103.05630","title":"ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis","created":"2021-03-09","cited_by_count":126,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"id":"2206.06931","title":"Stand-Alone Inter-Frame Attention in Video Models","created":"2022-06-14","cited_by_count":19,"area":null},{"id":"2301.00986","title":"Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition","created":"2023-01-03","cited_by_count":7,"area":null},{"id":"2206.10491","title":"Bi-Calibration Networks for Weakly-Supervised Video Representation Learning","created":"2022-06-21","cited_by_count":4,"area":null},{"id":"2103.13512","title":"Projection: A Mechanism for Human-like Reasoning in Artificial Intelligence","created":"2021-03-24","cited_by_count":2,"area":null},{"id":"2112.08325","title":"ForgeryNet -- Face Forgery Analysis Challenge 2021: Methods and Results","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2406.14206","title":"Live Video Captioning","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2106.11335","title":"Do sound event representations generalize to other audio tasks? A case study in audio transfer learning","created":"2021-06-21","cited_by_count":1,"area":null},{"id":"2301.06082","title":"A Survey on Human Action Recognition","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2409.10641","title":"HAVANA: Hierarchical stochastic neighbor embedding for Accelerated Video ANnotAtions","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2606.09289","title":"Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":null}