AAAI 2024 accepted papers on Detection and segmentation

Open-set and few-shot detection · 63 papers

• SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation (107 citations)
• CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models (69 citations)
• UV-SAM: Adapting Segment Anything Model for Urban Village Identification (57 citations)
• Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects (52 citations)
• Learning Content-Enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation (50 citations)
• Object-Aware Domain Generalization for Object Detection (47 citations)
• Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection (37 citations)
• Improving Audio-Visual Segmentation with Bidirectional Generation (32 citations)
• Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation (29 citations)
• CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation (25 citations)
• Simple Image-Level Classification Improves Open-Vocabulary Object Detection (25 citations)
• G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection (23 citations)

and 51 more in the interactive map.

CNN features · 48 papers

• SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation (178 citations)
• Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection (84 citations)
• Fine-Grained Prototypes Distillation for Few-Shot Object Detection (68 citations)
• AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection (58 citations)
• Spatial Transform Decoupling for Oriented Object Detection (54 citations)
• TOP-ReID: Multi-Spectral Object Re-identification with Token Permutation (49 citations)
• Attention Guided CAM: Visual Explanations of Vision Transformer Guided by Self-Attention (39 citations)
• TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection (39 citations)
• DeS3: Adaptive Attention-Driven Self and Soft Shadow Removal Using ViT Similarity (38 citations)
• GLH-Water: A Large-Scale Dataset for Global Surface Water Detection in Large-Size Very-High-Resolution Satellite Imagery (38 citations)
• Polyper: Boundary Sensitive Polyp Segmentation (37 citations)
• Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (28 citations)

and 36 more in the interactive map.

3D detection and driving · 18 papers

• DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving (97 citations)
• Far3D: Expanding the Horizon for Surround-View 3D Object Detection (73 citations)
• DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection (48 citations)
• SimDistill: Simulated Multi-Modal Distillation for BEV 3D Object Detection (23 citations)
• SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection (22 citations)
• FD3D: Exploiting Foreground Depth Map for Feature-Supervised Monocular 3D Object Detection (17 citations)
• Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection (17 citations)
• SOGDet: Semantic-Occupancy Guided Multi-View 3D Object Detection (16 citations)
• FM-OV3D: Foundation Model-Based Cross-Modal Knowledge Blending for Open-Vocabulary 3D Detection (13 citations)
• Instance-Aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning (12 citations)
• SwiftPillars: High-Efficiency Pillar Encoder for Lidar-Based 3D Detection (12 citations)
• CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection (11 citations)

and 6 more in the interactive map.

Weakly supervised detection and segmentation · 12 papers

• Weakly-Supervised Mirror Detection via Scribble Annotations (21 citations)
• Weakly Supervised Open-Vocabulary Object Detection (20 citations)
• Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label (17 citations)
• Weakly Supervised Semantic Segmentation for Driving Scenes (14 citations)
• Dual-Perspective Knowledge Enrichment for Semi-supervised 3D Object Detection (11 citations)
• Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (11 citations)
• Weakly Supervised Few-Shot Object Detection with DETR (9 citations)
• WeakPCSOD: Overcoming the Bias of Box Annotations for Weakly Supervised Point Cloud Salient Object Detection (8 citations)
• MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Driving (7 citations)
• Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection (4 citations)
• Fully Data-Driven Pseudo Label Estimation for Pointly-Supervised Panoptic Segmentation (3 citations)
• W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (2 citations)

Tracking · 11 papers

• ODTrack: Online Dense Temporal Token Learning for Visual Tracking (200 citations)
• Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking (173 citations)
• UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation (115 citations)
• Explicit Visual Prompts for Visual Object Tracking (105 citations)
• SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking (83 citations)
• Temporal Adaptive RGBT Tracking with Modality Prompt (83 citations)
• DiffusionTrack: Diffusion Model for Multi-Object Tracking (66 citations)
• Sequential Fusion Based Multi-Granularity Consistency for Space-Time Transformer Tracking (14 citations)
• CTO-SLAM: Contour Tracking for Object-Level Robust 4D SLAM (6 citations)
• Sampling-Resilient Multi-Object Tracking (6 citations)
• Learning Random Noise Salient Feature Fusion Siamese Network for Low-Resolution Object Tracking (Student Abstract) (3 citations)