{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"1903.03326","title":"Knowledge-Embedded Routing Network for Scene Graph Generation","created":"2019-03-08","cited_by_count":164},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"1903.02728","title":"Graphical Contrastive Losses for Scene Graph Parsing","created":"2019-03-07","cited_by_count":100},{"id":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"id":"1806.11538","title":"Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation","created":"2018-06-29","cited_by_count":78},{"id":"2009.00893","title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","created":"2020-09-02","cited_by_count":75},{"id":"2003.12929","title":"Superpixel Segmentation with Fully Convolutional Networks","created":"2020-03-29","cited_by_count":72},{"id":"2107.02112","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","created":"2021-07-05","cited_by_count":71},{"id":"2203.09811","title":"Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation","created":"2022-03-18","cited_by_count":67},{"id":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57},{"id":"2203.11654","title":"Fine-Grained Scene Graph Generation with Data Transfer","created":"2022-03-22","cited_by_count":57},{"id":"2211.11427","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","created":"2022-11-21","cited_by_count":57},{"id":"2007.01072","title":"Scene Graph Reasoning for Visual Question Answering","created":"2020-07-02","cited_by_count":50},{"id":"2303.14369","title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","created":"2023-03-25","cited_by_count":45},{"id":"2305.13803","title":"NORM: Knowledge Distillation via N-to-One Representation Matching","created":"2023-05-23","cited_by_count":44},{"id":"2303.01494","title":"Image as Set of Points","created":"2023-03-02","cited_by_count":43},{"id":"2304.00733","title":"Unbiased Scene Graph Generation in Videos","created":"2023-04-03","cited_by_count":39},{"id":"2303.07096","title":"Prototype-based Embedding Network for Scene Graph Generation","created":"2023-03-13","cited_by_count":37},{"id":"2305.02187","title":"CLUSTSEG: Clustering for Universal Segmentation","created":"2023-05-03","cited_by_count":32},{"id":"2305.12218","title":"Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment","created":"2023-05-20","cited_by_count":32},{"id":"2203.13609","title":"Unsupervised Pre-training for Temporal Action Localization Tasks","created":"2022-03-25","cited_by_count":31},{"id":"2112.08996","title":"Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation","created":"2021-12-16","cited_by_count":29},{"id":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29},{"id":"2209.10326","title":"Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering","created":"2022-09-21","cited_by_count":25},{"id":"2304.03495","title":"Devil's on the Edges: Selective Quad Attention for Scene Graph Generation","created":"2023-04-07","cited_by_count":23},{"id":"2211.16636","title":"Iterative Scene Graph Generation with Generative Transformers","created":"2022-11-30","cited_by_count":22},{"id":"2111.13517","title":"Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation","created":"2021-11-26","cited_by_count":21},{"id":"2208.01834","title":"Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation","created":"2022-08-03","cited_by_count":20},{"id":"2305.08522","title":"Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs","created":"2023-05-15","cited_by_count":14},{"id":"2011.03308","title":"Towards Efficient Scene Understanding via Squeeze Reasoning","created":"2020-11-06","cited_by_count":10},{"id":"2211.06444","title":"Probabilistic Debiasing of Scene Graphs","created":"2022-11-11","cited_by_count":8},{"id":"2101.10696","title":"AINet+: Advancing Superpixel Segmentation via Cascaded Association Implantation","created":"2021-01-26","cited_by_count":6},{"id":"2007.04257","title":"Superpixel Segmentation using Dynamic and Iterative Spanning Forest","created":"2020-07-08","cited_by_count":5},{"id":"2205.07017","title":"Importance Weighted Structure Learning for Scene Graph Generation","created":"2022-05-14","cited_by_count":4}],"next_cursor":null}