{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"1811.07628","title":"ATOM: Accurate Tracking by Overlap Maximization","created":"2018-11-19","cited_by_count":285},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","cited_by_count":148},{"id":"1604.02748","title":"TGIF: A New Dataset and Benchmark on Animated GIF Description","created":"2016-04-10","cited_by_count":124},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115},{"id":"2303.10883","title":"Explicit Visual Prompting for Low-Level Structure Segmentations","created":"2023-03-20","cited_by_count":114},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107},{"id":"2003.13948","title":"Segmenting Transparent Objects in the Wild","created":"2020-03-31","cited_by_count":98},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91},{"id":"2004.09044","title":"Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense","created":"2020-04-20","cited_by_count":62},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53},{"id":"2007.15781","title":"LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities","created":"2020-07-31","cited_by_count":47},{"id":"2109.03413","title":"YouRefIt: Embodied Reference Understanding with Language and Gesture","created":"2021-09-08","cited_by_count":33},{"id":"2011.10875","title":"Transparent Object Tracking Benchmark","created":"2020-11-21","cited_by_count":19},{"id":"2303.13800","title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations","created":"2023-03-24","cited_by_count":10}],"next_cursor":null}