{"list":"other","total":107,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2209.14734","title":"DiGress: Discrete Denoising diffusion for graph generation","created":"2022-09-29","cited_by_count":520},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"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":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"2202.02514","title":"Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations","created":"2022-02-05","cited_by_count":283},{"id":"2112.00390","title":"SegDiff: Image Segmentation with Diffusion Probabilistic Models","created":"2021-12-01","cited_by_count":280},{"id":"2003.00638","title":"Permutation Invariant Graph Generation via Score-Based Generative Modeling","created":"2020-03-02","cited_by_count":270},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"2209.02646","title":"A Survey on Generative Diffusion Model","created":"2022-09-06","cited_by_count":240},{"id":"2206.09012","title":"Diffusion models as plug-and-play priors","created":"2022-06-17","cited_by_count":231},{"id":"2001.09099","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","created":"2020-01-24","cited_by_count":215},{"id":"2305.01140","title":"Geometric Latent Diffusion Models for 3D Molecule Generation","created":"2023-05-02","cited_by_count":186},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"1808.07962","title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","created":"2018-08-23","cited_by_count":176},{"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":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"2312.03209","title":"Cache Me if You Can: Accelerating Diffusion Models through Block Caching","created":"2023-12-06","cited_by_count":151},{"id":"1904.04357","title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","created":"2019-04-08","cited_by_count":146},{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103},{"id":"1904.00560","title":"Scene Graph Generation with External Knowledge and Image Reconstruction","created":"2019-04-01","cited_by_count":102},{"id":"1903.02728","title":"Graphical Contrastive Losses for Scene Graph Parsing","created":"2019-03-07","cited_by_count":100},{"id":"2210.06366","title":"A Generalist Framework for Panoptic Segmentation of Images and Videos","created":"2022-10-12","cited_by_count":99},{"id":"1704.03114","title":"Detecting Visual Relationships with Deep Relational Networks","created":"2017-04-11","cited_by_count":97},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"2302.14816","title":"Monocular Depth Estimation using Diffusion Models","created":"2023-02-28","cited_by_count":87},{"id":"2303.05021","title":"DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation","created":"2023-03-09","cited_by_count":82},{"id":"2009.00893","title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","created":"2020-09-02","cited_by_count":75},{"id":"1811.10696","title":"Attentive Relational Networks for Mapping Images to Scene Graphs","created":"2018-11-26","cited_by_count":73},{"id":"2308.04758","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","created":"2023-08-09","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":"2203.10202","title":"Relationformer: A Unified Framework for Image-to-Graph Generation","created":"2022-03-19","cited_by_count":67},{"id":"2108.09668","title":"Learning of Visual Relations: The Devil is in the Tails","created":"2021-08-22","cited_by_count":65},{"id":"1512.06974","title":"Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels","created":"2015-12-22","cited_by_count":64},{"id":"1707.09423","title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","created":"2017-07-28","cited_by_count":61},{"id":"2206.03014","title":"The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation","created":"2022-06-07","cited_by_count":60},{"id":"2403.02075","title":"DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction","created":"2024-03-04","cited_by_count":59},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58},{"id":"2209.14566","title":"Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation","created":"2022-09-29","cited_by_count":55},{"id":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52},{"id":"1811.06410","title":"LinkNet: Relational Embedding for Scene Graph","created":"2018-11-15","cited_by_count":45},{"id":"1807.04979","title":"Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition","created":"2018-07-13","cited_by_count":41},{"id":"1903.10547","title":"Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph","created":"2019-03-25","cited_by_count":41},{"id":"2211.07609","title":"PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation","created":"2022-11-14","cited_by_count":41},{"id":"1909.02144","title":"Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning","created":"2019-09-04","cited_by_count":40},{"id":"2003.04262","title":"Cascaded Human-Object Interaction Recognition","created":"2020-03-09","cited_by_count":40},{"id":"2308.09905","title":"DiffusionTrack: Diffusion Model For Multi-Object Tracking","created":"2023-08-19","cited_by_count":40},{"id":"2304.00733","title":"Unbiased Scene Graph Generation in Videos","created":"2023-04-03","cited_by_count":39},{"id":"2405.05224","title":"Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation","created":"2024-05-08","cited_by_count":37},{"id":"2005.08230","title":"Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation","created":"2020-05-17","cited_by_count":31},{"id":"2105.02170","title":"Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries","created":"2021-05-05","cited_by_count":31},{"id":"2112.09828","title":"Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs","created":"2021-12-18","cited_by_count":31},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31},{"id":"2311.04391","title":"3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features","created":"2023-11-07","cited_by_count":26},{"id":"2103.15365","title":"Visual Distant Supervision for Scene Graph Generation","created":"2021-03-29","cited_by_count":25},{"id":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25},{"id":"2112.04222","title":"Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs","created":"2021-12-08","cited_by_count":23},{"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":"2405.16925","title":"OED: Towards One-stage End-to-End Dynamic Scene Graph Generation","created":"2024-05-27","cited_by_count":23},{"id":"2211.16636","title":"Iterative Scene Graph Generation with Generative Transformers","created":"2022-11-30","cited_by_count":22},{"id":"2407.15087","title":"Navigation Instruction Generation with BEV Perception and Large Language Models","created":"2024-07-21","cited_by_count":21},{"id":"2207.13316","title":"NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation","created":"2022-07-27","cited_by_count":19},{"id":"2306.03437","title":"DFormer: Diffusion-guided Transformer for Universal Image Segmentation","created":"2023-06-06","cited_by_count":19},{"id":"2108.08363","title":"Social Fabric: Tubelet Compositions for Video Relation Detection","created":"2021-08-18","cited_by_count":18},{"id":"2404.04308","title":"Visual Knowledge in the Big Model Era: Retrospect and Prospect","created":"2024-04-05","cited_by_count":16},{"id":"2410.15364","title":"Scene Graph Generation with Role-Playing Large Language Models","created":"2024-10-20","cited_by_count":16},{"id":"2410.20155","title":"Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models","created":"2024-10-26","cited_by_count":15},{"id":"2011.02164","title":"An Improved Attention for Visual Question Answering","created":"2020-11-04","cited_by_count":14},{"id":"2305.08522","title":"Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs","created":"2023-05-15","cited_by_count":14},{"id":"2305.16397","title":"Are Diffusion Models Vision-And-Language Reasoners?","created":"2023-05-25","cited_by_count":14},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14},{"id":"1809.00204","title":"Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions","created":"2018-09-01","cited_by_count":13},{"id":"2303.08319","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","created":"2023-03-15","cited_by_count":11},{"id":"1806.04860","title":"Learning Visual Knowledge Memory Networks for Visual Question Answering","created":"2018-06-13","cited_by_count":10},{"id":"2409.10262","title":"Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation","created":"2024-09-16","cited_by_count":10},{"id":"2311.12682","title":"Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation","created":"2023-11-21","cited_by_count":9},{"id":"2308.04770","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","created":"2023-08-09","cited_by_count":7}],"next_cursor":"100"}