NeurIPS 2024 accepted papers on Detection and segmentation
126 of the 4,560 papers accepted at NeurIPS 2024 (2.8%) are on Detection and segmentation, compared with 3.0% at NeurIPS 2023. They fall into 5 topics.
See NeurIPS 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 · 67 papers
- SegVol: Universal and Interactive Volumetric Medical Image Segmentation (48 citations)
- DF40: Toward Next-Generation Deepfake Detection (42 citations)
- SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection (33 citations)
- SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation (30 citations)
- Segment Any Change (19 citations)
- Hybrid Mamba for Few-Shot Segmentation (16 citations)
- IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization (11 citations)
- Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation (11 citations)
- Bridge the Points: Graph-based Few-shot Segment Anything Semantically (10 citations)
- FT-AED: Benchmark Dataset for Early Freeway Traffic Anomalous Event Detection (10 citations)
- Flaws can be Applause: Unleashing Potential of Segmenting Ambiguous Objects in SAM (8 citations)
- Omnigrasp: Grasping Diverse Objects with Simulated Humanoids (8 citations)
and 55 more in the interactive map.
CNN features · 26 papers
- YOLOv10: Real-Time End-to-End Object Detection (1,586 citations)
- You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection (28 citations)
- E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection (26 citations)
- Can We Leave Deepfake Data Behind in Training Deepfake Detector? (25 citations)
- Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models (11 citations)
- AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection (10 citations)
- QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model (10 citations)
- MambaTree: Tree Topology is All You Need in State Space Model (7 citations)
- Efficient Temporal Action Segmentation via Boundary-aware Query Voting (6 citations)
- Accelerating Non-Maximum Suppression: A Graph Theory Perspective (5 citations)
- AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation (5 citations)
- DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model (5 citations)
and 14 more in the interactive map.
3D detection and driving · 19 papers
- Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data (11 citations)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (10 citations)
- Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond (9 citations)
- CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection (5 citations)
- DiffuBox: Refining 3D Object Detection with Point Diffusion (5 citations)
- SAM-Guided Masked Token Prediction for 3D Scene Understanding (5 citations)
- UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles (5 citations)
- UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes (5 citations)
- RETR: Multi-View Radar Detection Transformer for Indoor Perception (4 citations)
- Towards Learning Group-Equivariant Features for Domain Adaptive 3D Detection (4 citations)
- Is Your LiDAR Placement Optimized for 3D Scene Understanding? (3 citations)
- ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualization (1 citation)
and 7 more in the interactive map.
Tracking · 8 papers
- WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark (13 citations)
- VastTrack: Vast Category Visual Object Tracking (11 citations)
- BuckTales: A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes (4 citations)
- OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking (3 citations)
- Beyond Accuracy: Tracking more like Human via Visual Search (1 citation)
- DeTrack: In-model Latent Denoising Learning for Visual Object Tracking (1 citation)
- TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation (1 citation)
- Revisiting motion information for RGB-Event tracking with MOT philosophy
Weakly supervised detection and segmentation · 6 papers
- Open-Vocabulary Object Detection via Language Hierarchy (7 citations)
- Boosting Weakly Supervised Referring Image Segmentation via Progressive Comprehension (4 citations)
- Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets (4 citations)
- Segment Anything without Supervision (2 citations)
- Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation (1 citation)
- A New Multi-Source Light Detection Benchmark and Semi-Supervised Focal Light Detection