{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"2010.04592","title":"Contrastive Learning with Hard Negative Samples","created":"2020-10-09","cited_by_count":628},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"1605.08110","title":"Video Summarization with Long Short-term Memory","created":"2016-05-26","cited_by_count":142},{"id":"1910.14303","title":"Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos","created":"2019-10-31","cited_by_count":135},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135},{"id":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123},{"id":"2104.10054","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","created":"2021-04-20","cited_by_count":103},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95},{"id":"2103.08109","title":"Boundary Proposal Network for Two-Stage Natural Language Video Localization","created":"2021-03-15","cited_by_count":88},{"id":"1809.06181","title":"Dual Encoding for Zero-Example Video Retrieval","created":"2018-09-17","cited_by_count":85},{"id":"1904.03282","title":"Weakly Supervised Video Moment Retrieval From Text Queries","created":"2019-04-05","cited_by_count":85},{"id":"1811.08925","title":"MAC: Mining Activity Concepts for Language-based Temporal Localization","created":"2018-11-21","cited_by_count":84},{"id":"1803.09125","title":"Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition","created":"2018-03-24","cited_by_count":78},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74},{"id":"1805.10538","title":"Video Summarization Using Fully Convolutional Sequence Networks","created":"2018-05-26","cited_by_count":71},{"id":"1911.08199","title":"Weakly-Supervised Video Moment Retrieval via Semantic Completion Network","created":"2019-11-19","cited_by_count":69},{"id":"2103.16392","title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","created":"2021-03-30","cited_by_count":69},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63},{"id":"2105.06247","title":"Video Corpus Moment Retrieval with Contrastive Learning","created":"2021-05-13","cited_by_count":60},{"id":"2009.00325","title":"Uncovering Hidden Challenges in Query-Based Video Moment Retrieval","created":"2020-09-01","cited_by_count":58},{"id":"1901.01874","title":"Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions","created":"2019-01-07","cited_by_count":54},{"id":"2008.10238","title":"VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval","created":"2020-08-24","cited_by_count":41},{"id":"1909.13784","title":"LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval","created":"2019-09-27","cited_by_count":40},{"id":"2107.11443","title":"Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation","created":"2021-07-23","cited_by_count":39},{"id":"2106.16136","title":"Weakly Supervised Temporal Adjacent Network for Language Grounding","created":"2021-06-30","cited_by_count":37},{"id":"1909.00239","title":"WSLLN: Weakly Supervised Natural Language Localization Networks","created":"2019-08-31","cited_by_count":36},{"id":"2003.07048","title":"Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos","created":"2020-03-16","cited_by_count":31},{"id":"1808.04285","title":"Unsupervised Hard Example Mining from Videos for Improved Object Detection","created":"2018-08-13","cited_by_count":30},{"id":"2001.09308","title":"Look Closer to Ground Better: Weakly-Supervised Temporal Grounding of Sentence in Video","created":"2020-01-25","cited_by_count":29},{"id":"2008.08257","title":"Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos","created":"2020-08-19","cited_by_count":23},{"id":"2009.08614","title":"Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos","created":"2020-09-18","cited_by_count":23},{"id":"2311.15367","title":"BatchNorm-based Weakly Supervised Video Anomaly Detection","created":"2023-11-26","cited_by_count":22},{"id":"2210.08714","title":"Selective Query-guided Debiasing for Video Corpus Moment Retrieval","created":"2022-10-17","cited_by_count":18},{"id":"2102.01282","title":"Progressive Localization Networks for Language-based Moment Localization","created":"2021-02-02","cited_by_count":17},{"id":"2110.06058","title":"Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos","created":"2021-10-12","cited_by_count":16},{"id":"2408.03282","title":"AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval","created":"2024-08-06","cited_by_count":16},{"id":"2310.05241","title":"SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval","created":"2023-10-08","cited_by_count":13},{"id":"2212.07592","title":"Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration","created":"2022-12-15","cited_by_count":11},{"id":"2312.16388","title":"Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding","created":"2023-12-27","cited_by_count":10},{"id":"2308.05648","title":"Counterfactual Cross-modality Reasoning for Weakly Supervised Video Moment Localization","created":"2023-08-10","cited_by_count":7},{"id":"2401.07567","title":"Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video","created":"2024-01-15","cited_by_count":7},{"id":"2207.09280","title":"Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation","created":"2022-07-19","cited_by_count":5},{"id":"2308.12609","title":"Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localization","created":"2023-08-24","cited_by_count":4}],"next_cursor":null}