{"total":16,"rows":[{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226,"area":null},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225,"area":null},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79,"area":null},{"id":"2110.00111","title":"Deep Learning-based Action Detection in Untrimmed Videos: A Survey","created":"2021-09-30","cited_by_count":32,"area":null},{"id":"2407.01264","title":"SignCLIP: Connecting Text and Sign Language by Contrastive Learning","created":"2024-07-01","cited_by_count":20,"area":null},{"id":"2107.04362","title":"RGB Stream Is Enough for Temporal Action Detection","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2203.13371","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2207.10448","title":"An Efficient Spatio-Temporal Pyramid Transformer for Action Detection","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2204.00452","title":"Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition","created":"2022-04-01","cited_by_count":5,"area":null},{"id":"2204.07270","title":"Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition","created":"2022-04-15","cited_by_count":3,"area":null},{"id":"2406.02831","title":"Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2212.11187","title":"Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning","created":"2022-12-21","cited_by_count":2,"area":null},{"id":"2310.13585","title":"POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2312.00115","title":"A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2211.03895","title":"Facial Tic Detection in Untrimmed Videos of Tourette Syndrome Patients","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2311.15916","title":"ADM-Loc: Actionness Distribution Modeling for Point-supervised Temporal Action Localization","created":"2023-11-27","cited_by_count":0,"area":null}],"next_cursor":null}