{"list":"other","total":76,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"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":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"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":"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":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"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":"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":"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":"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":"1811.11524","title":"Multi-granularity Generator for Temporal Action Proposal","created":"2018-11-28","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":"2207.08184","title":"Zero-Shot Temporal Action Detection via Vision-Language Prompting","created":"2022-07-17","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":"2303.09813","title":"DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery","created":"2023-03-17","cited_by_count":54},{"id":"1908.06552","title":"Weakly-supervised Action Localization with Background Modeling","created":"2019-08-19","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":"2108.05029","title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","created":"2021-08-11","cited_by_count":42},{"id":"2112.03902","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","created":"2021-12-07","cited_by_count":42},{"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":"2203.16800","title":"Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization","created":"2022-03-31","cited_by_count":33},{"id":"1505.05957","title":"Joint Inference of Groups, Events and Human Roles in Aerial Videos","created":"2015-05-22","cited_by_count":30},{"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":"2203.05114","title":"OpenTAL: Towards Open Set Temporal Action Localization","created":"2022-03-10","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":"2111.12449","title":"Background-Click Supervision for Temporal Action Localization","created":"2021-11-24","cited_by_count":21},{"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":"1908.02422","title":"Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization","created":"2019-08-07","cited_by_count":14},{"id":"2210.02578","title":"AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation","created":"2022-10-05","cited_by_count":14},{"id":"2302.09850","title":"Constraint and Union for Partially-Supervised Temporal Sentence Grounding","created":"2023-02-20","cited_by_count":14},{"id":"1805.11333","title":"Pointly-Supervised Action Localization","created":"2018-05-29","cited_by_count":12},{"id":"2212.09335","title":"Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization","created":"2022-12-19","cited_by_count":12},{"id":"2012.09542","title":"Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN","created":"2020-12-17","cited_by_count":4},{"id":"1501.03069","title":"Learning from Multiple Sources for Video Summarisation","created":"2015-01-13","cited_by_count":2},{"id":"2210.01338","title":"Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning","created":"2022-10-04","cited_by_count":2}],"next_cursor":null}