{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"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":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"1901.06523","title":"Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks","created":"2019-01-19","cited_by_count":368},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1906.08988","title":"A Fourier Perspective on Model Robustness in Computer Vision","created":"2019-06-21","cited_by_count":288},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"1603.06180","title":"Segmentation from Natural Language Expressions","created":"2016-03-20","cited_by_count":257},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"1911.02855","title":"Dice Loss for Data-imbalanced NLP Tasks","created":"2019-11-07","cited_by_count":182},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"1807.01251","title":"Training behavior of deep neural network in frequency domain","created":"2018-07-03","cited_by_count":174},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"2205.07839","title":"Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization","created":"2022-05-16","cited_by_count":150},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143},{"id":"2001.06810","title":"See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks","created":"2020-01-19","cited_by_count":138},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"2105.01839","title":"Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation","created":"2021-05-05","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":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2206.04403","title":"VITA: Video Instance Segmentation via Object Token Association","created":"2022-06-09","cited_by_count":94},{"id":"2205.00823","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","created":"2022-05-02","cited_by_count":86},{"id":"1902.10322","title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning","created":"2019-02-27","cited_by_count":60},{"id":"2206.03789","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","created":"2022-06-08","cited_by_count":50},{"id":"2106.01061","title":"Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation","created":"2021-06-02","cited_by_count":42},{"id":"2305.18010","title":"Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models","created":"2023-05-29","cited_by_count":38},{"id":"2207.12622","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","created":"2022-07-26","cited_by_count":28},{"id":"2210.05567","title":"Global Spectral Filter Memory Network for Video Object Segmentation","created":"2022-10-11","cited_by_count":22},{"id":"2103.10702","title":"ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation","created":"2021-03-19","cited_by_count":21},{"id":"2005.14436","title":"Machine learning in spectral domain","created":"2020-05-29","cited_by_count":20},{"id":"2207.10258","title":"Region Aware Video Object Segmentation with Deep Motion Modeling","created":"2022-07-21","cited_by_count":19},{"id":"2204.02547","title":"Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation","created":"2022-04-06","cited_by_count":18},{"id":"2111.10747","title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation","created":"2021-11-21","cited_by_count":14},{"id":"2108.00399","title":"Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition","created":"2021-08-01","cited_by_count":12},{"id":"2107.12569","title":"Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation","created":"2021-07-27","cited_by_count":11},{"id":"2203.15969","title":"Deeply Interleaved Two-Stream Encoder for Referring Video Segmentation","created":"2022-03-30","cited_by_count":1}],"next_cursor":null}