ECCV 2024 accepted papers on Detection and segmentation
253 of the 2,387 papers accepted at ECCV 2024 (10.6%) are on Detection and segmentation, compared with 13.9% at ECCV 2022. They fall into 5 topics.
See ECCV 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Open-set and few-shot detection · 105 papers
- Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection (2,472 citations)
- A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization (124 citations)
- GRiT: A Generative Region-to-text Transformer for Object Understanding (111 citations)
- Diffusion Models for Open-Vocabulary Segmentation (96 citations)
- ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference (90 citations)
- Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively (90 citations)
- ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image (88 citations)
- CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation (72 citations)
- T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy (72 citations)
- ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation (70 citations)
- OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation (64 citations)
- I-MedSAM: Implicit Medical Image Segmentation with Segment Anything (63 citations)
and 93 more in the interactive map.
CNN features · 64 papers
- IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection (239 citations)
- Frequency-Spatial Entanglement Learning for Camouflaged Object Detection (126 citations)
- DQ-DETR: DETR with Dynamic Query for Tiny Object Detection (124 citations)
- Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation (122 citations)
- Segment and Recognize Anything at Any Granularity (110 citations)
- Integer-Valued Training and Spike-driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection (109 citations)
- Relation DETR: Exploring Explicit Position Relation Prior for Object Detection (90 citations)
- Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures (73 citations)
- DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs (70 citations)
- DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion (63 citations)
- Visible and Clear: Finding Tiny Objects in Difference Map (56 citations)
- Online Vectorized HD Map Construction using Geometry (46 citations)
and 52 more in the interactive map.
3D detection and driving · 44 papers
- V2X-Real: a Largs-Scale Dataset for Vehicle-to-Everything Cooperative Perception (94 citations)
- GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection (93 citations)
- Detecting As Labeling: Rethinking LiDAR-camera Fusion in 3D Object Detection (48 citations)
- SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection (42 citations)
- Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection (41 citations)
- SAMFusion: Sensor-Adaptive Multimodal Fusion for 3D Object Detection in Adverse Weather (40 citations)
- ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers (30 citations)
- Diffusion Model for Robust Multi-Sensor Fusion in 3D Object Detection and BEV Segmentation (24 citations)
- MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation (24 citations)
- LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection (22 citations)
- LISO: Lidar-only Self-Supervised 3D Object Detection (21 citations)
- OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection (21 citations)
and 32 more in the interactive map.
Weakly supervised detection and segmentation · 30 papers
- SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection (33 citations)
- Just a Hint: Point-Supervised Camouflaged Object Detection (24 citations)
- Crowd-SAM:SAM as a smart annotator for object detection in crowded scenes (23 citations)
- Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation (22 citations)
- DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation (21 citations)
- CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detection (19 citations)
- Learning Camouflaged Object Detection from Noisy Pseudo Label (19 citations)
- Diff3DETR: Agent-based Diffusion Model for Semi-supervised 3D Object Detection (14 citations)
- Diffusion-Guided Weakly Supervised Semantic Segmentation (14 citations)
- Self-supervised co-salient object detection via feature correspondences at multiple scales (12 citations)
- INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding (10 citations)
- Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation (10 citations)
and 18 more in the interactive map.
Tracking · 10 papers
- CoTracker: It is Better to Track Together (417 citations)
- Trackastra: Transformer-based cell tracking for live-cell microscopy (59 citations)
- Local All-Pair Correspondence for Point Tracking (49 citations)
- Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking (27 citations)
- Beyond MOT: Semantic Multi-Object Tracking (18 citations)
- "SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking" (10 citations)
- Exploring the Feature Extraction and Relation Modeling For Light-Weight Transformer Tracking (9 citations)
- VETRA: A Dataset for Vehicle Tracking in Aerial Imagery - New Challenges for Multi-Object Tracking (7 citations)
- OneTrack: Demystifying the Conflict Between Detection and Tracking in End-to-End 3D Trackers (5 citations)
- SemTrack: A Large-scale Dataset for Semantic Tracking in the Wild (2 citations)
