{"list":"other","total":65,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1903.06586","title":"Selective Kernel Networks","created":"2019-03-15","cited_by_count":403},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"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":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"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":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":226},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"1901.03784","title":"UPSNet: A Unified Panoptic Segmentation Network","created":"2019-01-12","cited_by_count":175},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143},{"id":"2008.01059","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","created":"2020-08-03","cited_by_count":138},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"2010.00514","title":"Referring Image Segmentation via Cross-Modal Progressive Comprehension","created":"2020-10-01","cited_by_count":131},{"id":"1704.03470","title":"Learning Two-Branch Neural Networks for Image-Text Matching Tasks","created":"2017-04-11","cited_by_count":119},{"id":"1909.07072","title":"A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension","created":"2019-09-16","cited_by_count":111},{"id":"1909.08164","title":"Dynamic Graph Attention for Referring Expression Comprehension","created":"2019-09-18","cited_by_count":111},{"id":"2105.01839","title":"Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation","created":"2021-05-05","cited_by_count":111},{"id":"1812.04794","title":"Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks","created":"2018-12-12","cited_by_count":102},{"id":"2010.00515","title":"Linguistic Structure Guided Context Modeling for Referring Image Segmentation","created":"2020-10-01","cited_by_count":102},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102},{"id":"1406.5679","title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping","created":"2014-06-22","cited_by_count":99},{"id":"1903.00839","title":"Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing","created":"2019-03-03","cited_by_count":88},{"id":"1712.01892","title":"Grounding Referring Expressions in Images by Variational Context","created":"2017-12-05","cited_by_count":82},{"id":"1711.08389","title":"Conditional Image-Text Embedding Networks","created":"2017-11-22","cited_by_count":50},{"id":"2206.03789","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","created":"2022-06-08","cited_by_count":50},{"id":"1911.09042","title":"Learning Cross-modal Context Graph for Visual Grounding","created":"2019-11-20","cited_by_count":49},{"id":"2001.04982","title":"Unifying Training and Inference for Panoptic Segmentation","created":"2020-01-14","cited_by_count":37},{"id":"1811.11683","title":"Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding","created":"2018-11-28","cited_by_count":32},{"id":"2105.06818","title":"Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation","created":"2021-05-14","cited_by_count":32},{"id":"2109.04988","title":"Panoptic Narrative Grounding","created":"2021-09-10","cited_by_count":27},{"id":"2008.04556","title":"Text as Neural Operator: Image Manipulation by Text Instruction","created":"2020-08-11","cited_by_count":26},{"id":"2011.10972","title":"Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning","created":"2020-11-22","cited_by_count":22},{"id":"1903.07669","title":"Neural Sequential Phrase Grounding (SeqGROUND)","created":"2019-03-18","cited_by_count":20},{"id":"2102.03026","title":"Instance and Panoptic Segmentation Using Conditional Convolutions","created":"2021-02-05","cited_by_count":19},{"id":"2104.06008","title":"Disentangled Motif-aware Graph Learning for Phrase Grounding","created":"2021-04-13","cited_by_count":17},{"id":"2110.04435","title":"Two-stage Visual Cues Enhancement Network for Referring Image Segmentation","created":"2021-10-09","cited_by_count":13},{"id":"2005.06035","title":"Cross-Modality Relevance for Reasoning on Language and Vision","created":"2020-05-12","cited_by_count":10}],"next_cursor":null}