{"list":"other","total":98,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"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":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2204.00227","title":"Perception Prioritized Training of Diffusion Models","created":"2022-04-01","cited_by_count":303},{"id":"2204.07141","title":"Masked Siamese Networks for Label-Efficient Learning","created":"2022-04-14","cited_by_count":302},{"id":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"2303.09522","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","created":"2023-03-16","cited_by_count":242},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"1907.13440","title":"MineRL: A Large-Scale Dataset of Minecraft Demonstrations","created":"2019-07-29","cited_by_count":215},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214},{"id":"1804.03142","title":"Markerless tracking of user-defined features with deep learning","created":"2018-04-09","cited_by_count":206},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169},{"id":"2005.06803","title":"TAM: Temporal Adaptive Module for Video Recognition","created":"2020-05-14","cited_by_count":139},{"id":"2303.13076","title":"CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching","created":"2023-03-23","cited_by_count":133},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"2307.12868","title":"Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry","created":"2023-07-24","cited_by_count":125},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"2310.01403","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","created":"2023-10-02","cited_by_count":118},{"id":"2204.08129","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","created":"2022-04-18","cited_by_count":103},{"id":"1907.12743","title":"Temporal Attentive Alignment for Large-Scale Video Domain Adaptation","created":"2019-07-30","cited_by_count":100},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99},{"id":"2301.05221","title":"Open-vocabulary Object Segmentation with Diffusion Models","created":"2023-01-12","cited_by_count":82},{"id":"1804.04412","title":"Unsupervised Discovery of Object Landmarks as Structural Representations","created":"2018-04-12","cited_by_count":73},{"id":"2403.00504","title":"Learning and Leveraging World Models in Visual Representation Learning","created":"2024-03-01","cited_by_count":72},{"id":"1711.09125","title":"Appearance-and-Relation Networks for Video Classification","created":"2017-11-24","cited_by_count":61},{"id":"2110.15128","title":"Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing","created":"2021-10-28","cited_by_count":49},{"id":"2409.03757","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","created":"2024-09-05","cited_by_count":49},{"id":"2412.03439","title":"CleanDIFT: Diffusion Features without Noise","created":"2024-12-04","cited_by_count":44},{"id":"2401.11739","title":"EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models","created":"2024-01-22","cited_by_count":43},{"id":"2310.00031","title":"Text-image Alignment for Diffusion-based Perception","created":"2023-09-29","cited_by_count":42},{"id":"1903.01038","title":"Spatiotemporal Pyramid Network for Video Action Recognition","created":"2019-03-04","cited_by_count":37},{"id":"2211.17115","title":"Multiresolution Textual Inversion","created":"2022-11-30","cited_by_count":34},{"id":"2403.12042","title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation","created":"2024-03-18","cited_by_count":27},{"id":"2112.05121","title":"Self-Supervised Keypoint Discovery in Behavioral Videos","created":"2021-12-09","cited_by_count":23},{"id":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19},{"id":"2312.00065","title":"Unsupervised Keypoints from Pretrained Diffusion Models","created":"2023-11-29","cited_by_count":15},{"id":"2409.10473","title":"MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion","created":"2024-09-16","cited_by_count":15},{"id":"1912.03716","title":"VideoDG: Generalizing Temporal Relations in Videos to Novel Domains","created":"2019-12-08","cited_by_count":14},{"id":"2303.13505","title":"A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition","created":"2023-03-23","cited_by_count":14},{"id":"2207.10553","title":"MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior","created":"2022-07-21","cited_by_count":12},{"id":"2405.16947","title":"Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models","created":"2024-05-27","cited_by_count":12},{"id":"2408.15241","title":"GenRec: Unifying Video Generation and Recognition with Diffusion Models","created":"2024-08-27","cited_by_count":11},{"id":"2307.10763","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","created":"2023-07-20","cited_by_count":8},{"id":"2410.18538","title":"SMITE: Segment Me In TimE","created":"2024-10-24","cited_by_count":7},{"id":"2411.17474","title":"Probing the Mid-level Vision Capabilities of Self-Supervised Learning","created":"2024-11-25","cited_by_count":7},{"id":"2207.01622","title":"Egocentric Video-Language Pretraining @ Ego4D Challenge 2022","created":"2022-07-04","cited_by_count":6},{"id":"2409.09455","title":"Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervision","created":"2024-09-14","cited_by_count":2}],"next_cursor":null}