{"list":"other","total":51,"rows":[{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"1910.07969","title":"On Completeness-aware Concept-Based Explanations in Deep Neural Networks","created":"2019-10-17","cited_by_count":239},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178},{"id":"1904.07911","title":"REPAIR: Removing Representation Bias by Dataset Resampling","created":"2019-04-16","cited_by_count":157},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144},{"id":"2006.15417","title":"Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors","created":"2020-06-27","cited_by_count":120},{"id":"1612.00341","title":"A Compositional Object-Based Approach to Learning Physical Dynamics","created":"2016-12-01","cited_by_count":119},{"id":"1912.05534","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","created":"2019-12-11","cited_by_count":117},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109},{"id":"2305.00729","title":"What Do Self-Supervised Vision Transformers Learn?","created":"2023-05-01","cited_by_count":93},{"id":"1807.10982","title":"Actor-Centric Relation Network","created":"2018-07-28","cited_by_count":87},{"id":"2212.06727","title":"What do Vision Transformers Learn? A Visual Exploration","created":"2022-12-13","cited_by_count":76},{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64},{"id":"2212.06200","title":"Breaking the \"Object\" in Video Object Segmentation","created":"2022-12-12","cited_by_count":49},{"id":"2306.09346","title":"Rosetta Neurons: Mining the Common Units in a Model Zoo","created":"2023-06-15","cited_by_count":46},{"id":"2212.03862","title":"Teaching Matters: Investigating the Role of Supervision in Vision Transformers","created":"2022-12-07","cited_by_count":45},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44},{"id":"2110.07858","title":"Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation","created":"2021-10-15","cited_by_count":40},{"id":"2210.06096","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","created":"2022-10-12","cited_by_count":39},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31},{"id":"2206.02846","title":"A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information","created":"2022-06-06","cited_by_count":26},{"id":"1807.06980","title":"Video Time: Properties, Encoders and Evaluation","created":"2018-07-18","cited_by_count":19},{"id":"2207.06261","title":"Is Appearance Free Action Recognition Possible?","created":"2022-07-13","cited_by_count":16},{"id":"2305.03052","title":"Tracking through Containers and Occluders in the Wild","created":"2023-05-04","cited_by_count":15},{"id":"2211.01783","title":"Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks","created":"2022-11-03","cited_by_count":7},{"id":"1612.00500","title":"Object-Centric Representation Learning from Unlabeled Videos","created":"2016-12-01","cited_by_count":3}],"next_cursor":null}