{"list":"other","total":83,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"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":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2112.05139","title":"CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields","created":"2021-12-09","cited_by_count":370},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"1804.07667","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","created":"2018-04-20","cited_by_count":194},{"id":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"2103.13137","title":"Learning Salient Boundary Feature for Anchor-free Temporal Action Localization","created":"2021-03-24","cited_by_count":156},{"id":"1703.03329","title":"UntrimmedNets for Weakly Supervised Action Recognition and Detection","created":"2017-03-09","cited_by_count":130},{"id":"1710.06236","title":"Single Shot Temporal Action Detection","created":"2017-10-17","cited_by_count":123},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"id":"2102.01894","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","created":"2021-02-03","cited_by_count":117},{"id":"1703.06189","title":"TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals","created":"2017-03-17","cited_by_count":113},{"id":"1703.01515","title":"CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos","created":"2017-03-04","cited_by_count":112},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112},{"id":"1712.05080","title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network","created":"2017-12-14","cited_by_count":100},{"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":"1807.10418","title":"W-TALC: Weakly-supervised Temporal Activity Localization and Classification","created":"2018-07-27","cited_by_count":87},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79},{"id":"1811.11524","title":"Multi-granularity Generator for Temporal Action Proposal","created":"2018-11-28","cited_by_count":77},{"id":"2011.11479","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","created":"2020-11-23","cited_by_count":77},{"id":"1807.08333","title":"AutoLoc: Weakly-supervised Temporal Action Localization","created":"2018-07-22","cited_by_count":75},{"id":"2008.09837","title":"Revisiting Anchor Mechanisms for Temporal Action Localization","created":"2020-08-22","cited_by_count":75},{"id":"1911.09963","title":"Background Suppression Network for Weakly-supervised Temporal Action Localization","created":"2019-11-22","cited_by_count":73},{"id":"2103.16392","title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","created":"2021-03-30","cited_by_count":69},{"id":"2009.07641","title":"BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation","created":"2020-09-15","cited_by_count":65},{"id":"2107.12960","title":"Enriching Local and Global Contexts for Temporal Action Localization","created":"2021-07-27","cited_by_count":64},{"id":"2003.06845","title":"SF-Net: Single-Frame Supervision for Temporal Action Localization","created":"2020-03-15","cited_by_count":62},{"id":"2003.12424","title":"Weakly-Supervised Action Localization by Generative Attention Modeling","created":"2020-03-27","cited_by_count":59},{"id":"1908.06552","title":"Weakly-supervised Action Localization with Background Modeling","created":"2019-08-19","cited_by_count":53},{"id":"2010.11594","title":"Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization","created":"2020-10-22","cited_by_count":53},{"id":"1908.08216","title":"3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization","created":"2019-08-22","cited_by_count":52},{"id":"2004.00163","title":"Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning","created":"2020-03-31","cited_by_count":48},{"id":"1807.04821","title":"CTAP: Complementary Temporal Action Proposal Generation","created":"2018-07-12","cited_by_count":46},{"id":"2101.00545","title":"A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization","created":"2021-01-03","cited_by_count":45},{"id":"2206.12772","title":"Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation","created":"2022-06-26","cited_by_count":44},{"id":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44},{"id":"2108.05029","title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","created":"2021-08-11","cited_by_count":42},{"id":"2011.10830","title":"Boundary-sensitive Pre-training for Temporal Localization in Videos","created":"2020-11-21","cited_by_count":41},{"id":"2007.06643","title":"Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization","created":"2020-07-13","cited_by_count":40},{"id":"2203.15187","title":"ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization","created":"2022-03-29","cited_by_count":40},{"id":"2204.02932","title":"An Empirical Study of End-to-End Temporal Action Detection","created":"2022-04-06","cited_by_count":40},{"id":"2107.12589","title":"Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization","created":"2021-07-27","cited_by_count":34},{"id":"2203.16800","title":"Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization","created":"2022-03-31","cited_by_count":33},{"id":"2203.02925","title":"Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation","created":"2022-03-06","cited_by_count":32},{"id":"2203.13609","title":"Unsupervised Pre-training for Temporal Action Localization Tasks","created":"2022-03-25","cited_by_count":31},{"id":"1505.05957","title":"Joint Inference of Groups, Events and Human Roles in Aerial Videos","created":"2015-05-22","cited_by_count":30},{"id":"1807.02929","title":"Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector","created":"2018-07-09","cited_by_count":27},{"id":"2104.14135","title":"Action Unit Memory Network for Weakly Supervised Temporal Action Localization","created":"2021-04-29","cited_by_count":26},{"id":"2108.06524","title":"Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization","created":"2021-08-14","cited_by_count":26},{"id":"2203.07112","title":"RCL: Recurrent Continuous Localization for Temporal Action Detection","created":"2022-03-14","cited_by_count":25},{"id":"2012.06440","title":"D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations","created":"2020-12-11","cited_by_count":23},{"id":"1811.07460","title":"Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection","created":"2018-11-19","cited_by_count":22},{"id":"2012.08236","title":"Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses","created":"2020-12-15","cited_by_count":20},{"id":"2104.02357","title":"Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization","created":"2021-04-06","cited_by_count":18},{"id":"2112.10977","title":"ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization","created":"2021-12-21","cited_by_count":17},{"id":"2103.13183","title":"The Blessings of Unlabeled Background in Untrimmed Videos","created":"2021-03-24","cited_by_count":16},{"id":"2112.07984","title":"Temporal Action Proposal Generation with Background Constraint","created":"2021-12-15","cited_by_count":16}],"next_cursor":null}