CVPR 2024 accepted papers on Detection and segmentation
296 of the 2,716 papers accepted at CVPR 2024 (10.9%) are on Detection and segmentation, compared with 14.1% at CVPR 2023. They fall into 5 topics.
See CVPR 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Open-set and few-shot detection · 152 papers
- YOLO-World: Real-Time Open-Vocabulary Object Detection (721 citations)
- EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything (240 citations)
- AnyDoor: Zero-shot Object-level Image Customization (175 citations)
- VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning (129 citations)
- Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection (127 citations)
- SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation (123 citations)
- Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation (101 citations)
- Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation (92 citations)
- Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping (85 citations)
- Diffuse Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion (79 citations)
- OMG-Seg: Is One Model Good Enough For All Segmentation? (77 citations)
- VRP-SAM: SAM with Visual Reference Prompt (73 citations)
and 140 more in the interactive map.
CNN features · 55 papers
- DETRs Beat YOLOs on Real-time Object Detection (4,429 citations)
- Poly Kernel Inception Network for Remote Sensing Detection (528 citations)
- TransNeXt: Robust Foveal Visual Perception for Vision Transformers (401 citations)
- Infrared Small Target Detection with Scale and Location Sensitivity (253 citations)
- Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection (200 citations)
- Frequency-Adaptive Dilated Convolution for Semantic Segmentation (144 citations)
- Putting the Object Back into Video Object Segmentation (132 citations)
- Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement (119 citations)
- Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention (107 citations)
- Depth-Aware Concealed Crop Detection in Dense Agricultural Scenes (96 citations)
- Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection (84 citations)
- SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation (81 citations)
and 43 more in the interactive map.
3D detection and driving · 40 papers
- RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection (133 citations)
- IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection (118 citations)
- TUMTraf V2X Cooperative Perception Dataset (110 citations)
- PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation (82 citations)
- SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection (78 citations)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (73 citations)
- BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection (59 citations)
- MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception (57 citations)
- Towards Robust 3D Object Detection with LiDAR and 4D Radar Fusion in Various Weather Conditions (44 citations)
- RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features (43 citations)
- Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles (36 citations)
- CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation (35 citations)
and 28 more in the interactive map.
Weakly supervised detection and segmentation · 27 papers
- CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation (94 citations)
- From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation (80 citations)
- RankMatch: Exploring the Better Consistency Regularization for Semi-supervised Semantic Segmentation (63 citations)
- AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation (55 citations)
- Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation (54 citations)
- Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation (54 citations)
- Class Tokens Infusion for Weakly Supervised Semantic Segmentation (51 citations)
- PointOBB: Learning Oriented Object Detection via Single Point Supervision (50 citations)
- Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels (48 citations)
- DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation (46 citations)
- Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection (45 citations)
- Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision (43 citations)
and 15 more in the interactive map.
Tracking · 22 papers
- Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers (160 citations)
- OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning (139 citations)
- Single-Model and Any-Modality for Video Object Tracking (111 citations)
- DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction (73 citations)
- Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline (69 citations)
- DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking (43 citations)
- Matching Anything by Segmenting Anything (41 citations)
- Towards Generalizable Multi-Object Tracking (36 citations)
- ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association (32 citations)
- Delving into the Trajectory Long-tail Distribution for Muti-object Tracking (28 citations)
- LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry (27 citations)
- Multi-Object Tracking in the Dark (27 citations)
and 10 more in the interactive map.