{"list":"other","total":56,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1508.01991","title":"Bidirectional LSTM-CRF Models for Sequence Tagging","created":"2015-08-09","cited_by_count":546},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"2004.00849","title":"Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers","created":"2020-04-02","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":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"1808.02559","title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval","created":"2018-08-07","cited_by_count":208},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"2104.12099","title":"Visual Saliency Transformer","created":"2021-04-25","cited_by_count":175},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"id":"2003.10477","title":"Distilling Knowledge from Graph Convolutional Networks","created":"2020-03-23","cited_by_count":129},{"id":"1703.07939","title":"Recurrent Multimodal Interaction for Referring Image Segmentation","created":"2017-03-23","cited_by_count":125},{"id":"1604.02748","title":"TGIF: A New Dataset and Benchmark on Animated GIF Description","created":"2016-04-10","cited_by_count":124},{"id":"1803.07485","title":"Actor and Action Video Segmentation from a Sentence","created":"2018-03-20","cited_by_count":106},{"id":"2103.16284","title":"Locate then Segment: A Strong Pipeline for Referring Image Segmentation","created":"2021-03-30","cited_by_count":98},{"id":"2108.03151","title":"Full-Duplex Strategy for Video Object Segmentation","created":"2021-08-06","cited_by_count":78},{"id":"1701.05384","title":"FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos","created":"2017-01-19","cited_by_count":77},{"id":"1909.07061","title":"Motion Guided Attention for Video Salient Object Detection","created":"2019-09-16","cited_by_count":72},{"id":"2003.04253","title":"Motion-Attentive Transition for Zero-Shot Video Object Segmentation","created":"2020-03-09","cited_by_count":62},{"id":"2102.13558","title":"Natural Language Video Localization: A Revisit in Span-based Question Answering Framework","created":"2021-02-26","cited_by_count":55},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46},{"id":"2105.06818","title":"Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation","created":"2021-05-14","cited_by_count":32},{"id":"2104.02391","title":"Weakly Supervised Video Salient Object Detection","created":"2021-04-06","cited_by_count":28},{"id":"2109.09920","title":"Survey: Transformer based Video-Language Pre-training","created":"2021-09-21","cited_by_count":27},{"id":"2010.00263","title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","created":"2020-10-01","cited_by_count":23}],"next_cursor":null}