{"list":"other","total":55,"rows":[{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"1910.01279","title":"Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks","created":"2019-10-03","cited_by_count":582},{"id":"1812.04798","title":"Strong-Weak Distribution Alignment for Adaptive Object Detection","created":"2018-12-12","cited_by_count":270},{"id":"1503.01640","title":"BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation","created":"2015-03-05","cited_by_count":238},{"id":"1803.11365","title":"Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation","created":"2018-03-30","cited_by_count":218},{"id":"2008.00299","title":"Eigen-CAM: Class Activation Map using Principal Components","created":"2020-08-01","cited_by_count":189},{"id":"1604.03605","title":"What do different evaluation metrics tell us about saliency models?","created":"2016-04-12","cited_by_count":185},{"id":"1804.06962","title":"Adversarial Complementary Learning for Weakly Supervised Object Localization","created":"2018-04-19","cited_by_count":166},{"id":"2008.02312","title":"Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs","created":"2020-08-05","cited_by_count":151},{"id":"2007.01947","title":"Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation","created":"2020-07-03","cited_by_count":144},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"1908.01224","title":"Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models","created":"2019-08-03","cited_by_count":118},{"id":"2003.07685","title":"Weakly-Supervised Salient Object Detection via Scribble Annotations","created":"2020-03-17","cited_by_count":96},{"id":"1911.08039","title":"Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach","created":"2019-11-19","cited_by_count":88},{"id":"2001.06807","title":"Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks","created":"2020-01-19","cited_by_count":84},{"id":"2003.05477","title":"Unified Image and Video Saliency Modeling","created":"2020-03-11","cited_by_count":75},{"id":"1807.08902","title":"Self-produced Guidance for Weakly-supervised Object Localization","created":"2018-07-24","cited_by_count":72},{"id":"1909.07061","title":"Motion Guided Attention for Video Salient Object Detection","created":"2019-09-16","cited_by_count":72},{"id":"1904.05647","title":"C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection","created":"2019-04-11","cited_by_count":71},{"id":"1705.02544","title":"Deep Visual Attention Prediction","created":"2017-05-07","cited_by_count":70},{"id":"1801.07424","title":"Revisiting Video Saliency: A Large-scale Benchmark and a New Model","created":"2018-01-23","cited_by_count":67},{"id":"1701.01081","title":"SalGAN: Visual Saliency Prediction with Generative Adversarial Networks","created":"2017-01-04","cited_by_count":65},{"id":"1908.05786","title":"TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection","created":"2019-08-15","cited_by_count":59},{"id":"2012.05007","title":"Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation","created":"2020-12-09","cited_by_count":52},{"id":"1909.04972","title":"WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection","created":"2019-09-11","cited_by_count":51},{"id":"2006.14255","title":"SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization","created":"2020-06-25","cited_by_count":46},{"id":"1902.06057","title":"Min-Entropy Latent Model for Weakly Supervised Object Detection","created":"2019-02-16","cited_by_count":45},{"id":"1904.00566","title":"Multi-source weak supervision for saliency detection","created":"2019-04-01","cited_by_count":43},{"id":"1603.00845","title":"Shallow and Deep Convolutional Networks for Saliency Prediction","created":"2016-03-02","cited_by_count":42},{"id":"2001.03063","title":"STAViS: Spatio-Temporal AudioVisual Saliency Network","created":"2020-01-09","cited_by_count":40},{"id":"1811.02233","title":"Weakly Supervised Scene Parsing with Point-based Distance Metric Learning","created":"2018-11-06","cited_by_count":33},{"id":"1907.10164","title":"Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection","created":"2019-07-23","cited_by_count":31},{"id":"2006.12884","title":"SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection","created":"2020-06-23","cited_by_count":29},{"id":"2010.03023","title":"IS-CAM: Integrated Score-CAM for axiomatic-based explanations","created":"2020-10-06","cited_by_count":29},{"id":"2007.09943","title":"TENet: Triple Excitation Network for Video Salient Object Detection","created":"2020-07-20","cited_by_count":26},{"id":"1605.07651","title":"Self Paced Deep Learning for Weakly Supervised Object Detection","created":"2016-05-24","cited_by_count":25},{"id":"1907.01869","title":"Simple vs complex temporal recurrences for video saliency prediction","created":"2019-07-03","cited_by_count":25},{"id":"2010.01220","title":"Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction","created":"2020-10-02","cited_by_count":24},{"id":"1811.10016","title":"Dissimilarity Coefficient based Weakly Supervised Object Detection","created":"2018-11-25","cited_by_count":23},{"id":"1905.10693","title":"DAVE: A Deep Audio-Visual Embedding for Dynamic Saliency Prediction","created":"2019-05-25","cited_by_count":21},{"id":"1403.1626","title":"Can Image-Level Labels Replace Pixel-Level Labels for Image Parsing","created":"2014-03-07","cited_by_count":15},{"id":"1711.06778","title":"Excitation Backprop for RNNs","created":"2017-11-18","cited_by_count":14},{"id":"1710.03011","title":"Personalized Saliency and its Prediction","created":"2017-10-09","cited_by_count":13},{"id":"1907.07613","title":"Visual Tracking via Dynamic Memory Networks","created":"2019-07-12","cited_by_count":11},{"id":"1904.01665","title":"Activity Driven Weakly Supervised Object Detection","created":"2019-04-02","cited_by_count":9},{"id":"1809.07988","title":"SG-FCN: A Motion and Memory-Based Deep Learning Model for Video Saliency Detection","created":"2018-09-21","cited_by_count":6},{"id":"1706.02189","title":"Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation","created":"2017-06-06","cited_by_count":3},{"id":"1708.02459","title":"Weakly Supervised Image Annotation and Segmentation with Objects and Attributes","created":"2017-08-08","cited_by_count":3},{"id":"1710.04647","title":"Progressive Representation Adaptation for Weakly Supervised Object Localization","created":"2017-10-12","cited_by_count":2},{"id":"2109.08371","title":"Audio-Visual Collaborative Representation Learning for Dynamic Saliency Prediction","created":"2021-09-17","cited_by_count":2}],"next_cursor":null}