{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"1912.02424","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","created":"2019-12-05","cited_by_count":540},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2103.13137","title":"Learning Salient Boundary Feature for Anchor-free Temporal Action Localization","created":"2021-03-24","cited_by_count":156},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151},{"id":"2001.08740","title":"Audiovisual SlowFast Networks for Video Recognition","created":"2020-01-23","cited_by_count":146},{"id":"1909.03877","title":"Gaussian Temporal Awareness Networks for Action Localization","created":"2019-09-09","cited_by_count":135},{"id":"2102.01894","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","created":"2021-02-03","cited_by_count":117},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112},{"id":"2011.14598","title":"Video Self-Stitching Graph Network for Temporal Action Localization","created":"2020-11-30","cited_by_count":104},{"id":"1911.04127","title":"Fast Learning of Temporal Action Proposal via Dense Boundary Generator","created":"2019-11-11","cited_by_count":89},{"id":"2008.01432","title":"Boundary Content Graph Neural Network for Temporal Action Proposal Generation","created":"2020-08-04","cited_by_count":88},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79},{"id":"2011.11479","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","created":"2020-11-23","cited_by_count":77},{"id":"2008.09837","title":"Revisiting Anchor Mechanisms for Temporal Action Localization","created":"2020-08-22","cited_by_count":75},{"id":"2107.12960","title":"Enriching Local and Global Contexts for Temporal Action Localization","created":"2021-07-27","cited_by_count":64},{"id":"2012.09434","title":"Multi-shot Temporal Event Localization: a Benchmark","created":"2020-12-17","cited_by_count":52},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41},{"id":"2101.03682","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","created":"2021-01-11","cited_by_count":36},{"id":"2109.02613","title":"Class Semantics-based Attention for Action Detection","created":"2021-09-06","cited_by_count":36},{"id":"2112.03612","title":"DCAN: Improving Temporal Action Detection via Dual Context Aggregation","created":"2021-12-07","cited_by_count":36},{"id":"2207.06580","title":"Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning","created":"2022-07-14","cited_by_count":29},{"id":"2205.02717","title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","created":"2022-05-05","cited_by_count":28},{"id":"2303.09055","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","created":"2023-03-16","cited_by_count":28},{"id":"2103.16024","title":"Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation","created":"2021-03-30","cited_by_count":25},{"id":"2106.14118","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","created":"2021-06-27","cited_by_count":21},{"id":"1908.00707","title":"Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos","created":"2019-08-02","cited_by_count":17},{"id":"2105.12043","title":"Temporal Action Proposal Generation with Transformers","created":"2021-05-25","cited_by_count":17},{"id":"2207.10448","title":"An Efficient Spatio-Temporal Pyramid Transformer for Action Detection","created":"2022-07-21","cited_by_count":16},{"id":"2309.05590","title":"Temporal Action Localization with Enhanced Instant Discriminability","created":"2023-09-11","cited_by_count":13},{"id":"2205.09956","title":"Structured Attention Composition for Temporal Action Localization","created":"2022-05-20","cited_by_count":7},{"id":"2211.14924","title":"Post-Processing Temporal Action Detection","created":"2022-11-27","cited_by_count":6},{"id":"2202.04947","title":"OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos","created":"2022-02-10","cited_by_count":4},{"id":"2207.09662","title":"HTNet: Anchor-free Temporal Action Localization with Hierarchical Transformers","created":"2022-07-20","cited_by_count":4}],"next_cursor":null}