COCO

Common Objects in Context — 330k images with object-detection, segmentation, keypoint, and captioning annotations.

Papers using COCO (111)

Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval2026Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation2022 · 63 citesHSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition2026Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective2026FRFDet: Efficient UAV Small Object Detection with Symmetric Sampling and Scalable Fusion2026Repurposing CLIP to Localize at Pixel Level2026Confidence Scores in Open-Vocabulary Detection Are a Biased Mixture of Scale and Semantics2026Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoders2026Inhibited Self-Attention: Sharpening Focus in Vision Transformers2026Practical Insights into Semi-Supervised Object Detection Approaches2026Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation2025 · 1 citesLINEA: Fast and Accurate Line Detection Using Scalable Transformers2025 · 1 citesTeach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection2025 · 1 citesYOLOv4: A Breakthrough in Real-Time Object Detection2025 · 1 citesUnveiling the Unknown: Open Vocabulary Object Detection with Scene Graphs2026Training-Free Metrics for Synthetic Object Detection Data: A Proxy for Detector Performance2026A Turbo-Inference Strategy for Object Detection and Instance Segmentation2026What Helps---and What Hurts: Bidirectional Explanations for Vision Transformers2026Exploring Open-Vocabulary Object Recognition in Images using CLIP2026YOLO Object Detectors for Robotics -- a Comparative Study2026Enhancing Open-Vocabulary Object Detection through Multi-Level Fine-Grained Visual-Language Alignment2026Le-DETR: Revisiting Real-Time Detection Transformer with Efficient Encoder Design2026ZENITH: Automated Gradient Norm Informed Stochastic Optimization2026SSR: Semantic and Spatial Rectification for CLIP-based Weakly Supervised Segmentation2025Diffusion Is Your Friend in Show, Suggest and Tell2025LAPX: Lightweight Hourglass Network with Global Context2025Multi-label Classification with Panoptic Context Aggregation Networks2025DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture2025Utilizing dynamic sparsity on pretrained DETR2025A Training-Free Framework for Open-Vocabulary Image Segmentation and Recognition with EfficientNet and CLIP2025PyCAT4: A Hierarchical Vision Transformer-based Framework for 3D Human Pose Estimation2025LLM-Guided Agentic Object Detection for Open-World Understanding2025Test-time Vocabulary Adaptation for Language-driven Object Detection2025unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning2025Multiple Object Stitching for Unsupervised Representation Learning2025Pose Matters: Evaluating Vision Transformers and CNNs for Human Action Recognition on Small COCO Subsets2025Leveraging Vision-Language Pre-training for Human Activity Recognition in Still Images2025Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval2025Visual Textualization for Image Prompted Object Detection2025Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation2025The Missing Point in Vision Transformers for Universal Image Segmentation2025DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks2025Fractional Correspondence Framework in Detection Transformer2025Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation2025Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation2025Approximate Size Targets Are Sufficient for Accurate Semantic Segmentation2025Dynamic Relation Inference via Verb Embeddings2025Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient Segmentation2025LP-DETR: Layer-wise Progressive Relations for Object Detection2025Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation2024Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation2024Position Focused Attention Network For Image-text Matching2019 · 198 citesData Augmentation To Improve Robustness Of Image Captioning Solutions2021 · 1 citesCornerNet: Detecting Objects as Paired Keypoints2018 · 3,550 citesDeformable DETR: Deformable Transformers for End-to-End Object Detection2020 · 1,868 citesAssociative Embedding: End-to-End Learning for Joint Detection and Grouping2016 · 418 citesFew-Shot Object Detection with Fully Cross-Transformer2022 · 188 citesCPTR: Full Transformer Network for Image Captioning2021 · 109 citesImage Captioning: Transforming Objects into Words2019 · 93 citesConv2Former: A Simple Transformer-Style ConvNet for Visual Recognition2022 · 73 citesCausal Intervention for Weakly-Supervised Semantic Segmentation2020 · 70 citesOne-Shot Instance Segmentation2018 · 68 citesSelf-EMD: Self-Supervised Object Detection without ImageNet2020 · 67 citesComprehensive Attention Self-Distillation for Weakly-Supervised Object Detection2020 · 66 citesFace Detection Using Improved Faster RCNN2018 · 64 citesTFPose: Direct Human Pose Estimation with Transformers2021 · 57 citesISTR: End-to-End Instance Segmentation with Transformers2021 · 54 citesFully Convolutional Instance-aware Semantic Segmentation2016 · 38 citesEfficient Visual Pretraining with Contrastive Detection2021 · 33 citesUnsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision2021 · 31 citesMViTv2: Improved Multiscale Vision Transformers for Classification and Detection2021 · 29 citesCRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks2022 · 27 citesDiffusionInst: Diffusion Model for Instance Segmentation2022 · 23 citesFeature-Driven Super-Resolution for Object Detection2020 · 20 citesImplicit Feature Pyramid Network for Object Detection2020 · 19 citesMulti-class Token Transformer for Weakly Supervised Semantic Segmentation2022 · 19 citesEnd-to-End Object Detection with Fully Convolutional Network2020 · 14 citesDeep Occlusion-Aware Instance Segmentation with Overlapping BiLayers2021 · 8 citesCAT: Cross-Attention Transformer for One-Shot Object Detection2021 · 8 citesHierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning2022 · 8 citesUnderstanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields2023 · 7 citesTowards Few-Annotation Learning for Object Detection: Are Transformer-based Models More Efficient ?2023 · 5 citesT-VSE: Transformer-Based Visual Semantic Embedding2020 · 4 citesSpatial Reasoning for Few-Shot Object Detection2022 · 4 citesAnalysis of Visual Reasoning on One-Stage Object Detection2022 · 3 citesHCFormer: Unified Image Segmentation with Hierarchical Clustering2022 · 3 citesA Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting2024 · 3 citesPPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation2022 · 2 citesContextual Relabelling of Detected Objects2019 · 1 citesDETReg: Unsupervised Pretraining with Region Priors for Object Detection2021 · 1 citesTask Specific Attention is one more thing you need for object detection2022 · 1 citesTime-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detection2022 · 1 citesCan the Query-based Object Detector Be Designed with Fewer Stages?2023 · 1 citesIvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules2019Learning to Inpaint by Progressively Growing the Mask Regions2020Image Captioning using Multiple Transformers for Self-Attention Mechanism2021Modulating Localization and Classification for Harmonized Object Detection2021Poseur: Direct Human Pose Regression with Transformers2022ACORT: A Compact Object Relation Transformer for Parameter Efficient Image Captioning2022SeqCo-DETR: Sequence Consistency Training for Self-Supervised Object Detection with Transformers2023CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free2023COMNet: Co-Occurrent Matching for Weakly Supervised Semantic Segmentation2023DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation2023A Simple and Generalist Approach for Panoptic Segmentation2024COCO-OLAC: A Benchmark for Occluded Panoptic Segmentation and Image Understanding2024Waterfall Transformer for Multi-person Pose Estimation2024OPCap:Object-aware Prompting Captioning2024EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation2024Single-Shot Panoptic Segmentation2019PE-former: Pose Estimation Transformer2021Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation2022