{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197},{"id":"2303.13899","title":"Robust Test-Time Adaptation in Dynamic Scenarios","created":"2023-03-24","cited_by_count":189},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"1908.07325","title":"Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition","created":"2019-08-20","cited_by_count":116},{"id":"2008.01187","title":"PhraseCut: Language-based Image Segmentation in the Wild","created":"2020-08-03","cited_by_count":116},{"id":"2009.13000","title":"Interventional Few-Shot Learning","created":"2020-09-28","cited_by_count":112},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111},{"id":"2210.15871","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2022-10-28","cited_by_count":111},{"id":"1803.07485","title":"Actor and Action Video Segmentation from a Sentence","created":"2018-03-20","cited_by_count":106},{"id":"2002.12204","title":"Visual Commonsense R-CNN","created":"2020-02-27","cited_by_count":106},{"id":"2103.00887","title":"Counterfactual Zero-Shot and Open-Set Visual Recognition","created":"2021-03-01","cited_by_count":95},{"id":"2108.08782","title":"Causal Attention for Unbiased Visual Recognition","created":"2021-08-19","cited_by_count":80},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2003.03923","title":"Deconfounded Image Captioning: A Causal Retrospect","created":"2020-03-09","cited_by_count":65},{"id":"2207.12647","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","created":"2022-07-26","cited_by_count":57},{"id":"2205.14895","title":"From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering","created":"2022-05-30","cited_by_count":51},{"id":"2404.10241","title":"Vision-and-Language Navigation via Causal Learning","created":"2024-04-16","cited_by_count":51},{"id":"2207.01203","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","created":"2022-07-04","cited_by_count":50},{"id":"2212.06200","title":"Breaking the \"Object\" in Video Object Segmentation","created":"2022-12-12","cited_by_count":49},{"id":"2008.00923","title":"Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning","created":"2020-08-03","cited_by_count":46},{"id":"2008.06884","title":"DeVLBert: Learning Deconfounded Visio-Linguistic Representations","created":"2020-08-16","cited_by_count":42},{"id":"2308.11488","title":"Opening the Vocabulary of Egocentric Actions","created":"2023-08-22","cited_by_count":23},{"id":"2312.15715","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","created":"2023-12-25","cited_by_count":22},{"id":"2208.10156","title":"Meta-Causal Feature Learning for Out-of-Distribution Generalization","created":"2022-08-22","cited_by_count":14},{"id":"2311.09084","title":"Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search","created":"2023-11-15","cited_by_count":8},{"id":"2402.11265","title":"Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human Intentions","created":"2024-02-17","cited_by_count":8},{"id":"2407.07402","title":"ActionVOS: Actions as Prompts for Video Object Segmentation","created":"2024-07-10","cited_by_count":8},{"id":"2409.14205","title":"Egocentric zone-aware action recognition across environments","created":"2024-09-21","cited_by_count":6},{"id":"2311.10011","title":"SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting","created":"2023-11-16","cited_by_count":5},{"id":"2009.02980","title":"Efficient Projection Algorithms onto the Weighted l1 Ball","created":"2020-09-07","cited_by_count":4},{"id":"2508.05585","title":"DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition","created":"2025-08-07","cited_by_count":1}],"next_cursor":null}