Skip to content
conftrace_

Analysis

24,278 papers (19 classified directly here)

Subtopics · a paper can sit in several, so these overlap

3D Vision (8,497) Object Detection (5,109) Semantic Segmentation (3,186) Scene Understanding (2,031) Action Recognition (1,507) Depth Estimation (1,467) Human Pose Estimation (1,296) Object Tracking (1,140) Face Recognition (1,018) Anomaly Detection (975) Person Re-Identification (614) Image Classification (588) Motion Estimation (525) Object Segmentation (499) Human Analysis (444) Motion Analysis (376) Image Retrieval (336) Activity Recognition (327) Biometrics (265) Pose Estimation (262) Object Classification (158) Trajectory Prediction (125) Face Detection (107) Gait Recognition (66) Instance Segmentation (53) Multi-Object Tracking (38) Motion Segmentation (14) Gesture Recognition (14) Change Detection (13) Pedestrian Detection (10)

Papers per year

1
42
711
1,618
3,895
'5
'10
'15
'20
'25

Papers (including subtopics)

Toward Generalizable Whole Brain Representations with High-Resolution Light-Sheet Data CVPR 2026 Toward Low-Cost yet Effective Temporal Learning for UAV Tracking CVPR 2026 Towards 3D Object-Centric Feature Learning for Semantic Scene Completion AAAI 2026 Towards Accurate 3D Object Detection in Adverse Weather by Leveraging 4D Radar for LiDAR Geometry Enhancement AAAI 2026 Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation CVPR 2026 Towards Cross-Modal Preservation, Consistency and Alignment for Privacy-Preserving Visible-Infrared Person Re-Identification CVPR 2026 Towards Decompositional Human Motion Generation with Energy-Based Diffusion Models CVPR 2026 Towards Effective Surgical Representation Learning with DINO Models MIDL 2026 Towards Efficient and Effective Interactive 3D Segmentation AAAI 2026 Towards Egocentric 3D Hand Pose Estimation in Unseen Domains WACV 2026 Towards Explainable Video Camouflaged Object Detection: SAM2 with Eventstream-Inspired Data AAAI 2026 Towards Fast and Scalable Normal Integration using Continuous Components WACV 2026 Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds CVPR 2026 Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion AAAI 2026 Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation WACV 2026 Towards High-Quality Image Segmentation: Improving Topology Accuracy by Penalizing Neighbor Pixels CVPR 2026 Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defects AAAI 2026 Towards Intrinsic-Aware Monocular 3D Object Detection CVPR 2026 Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization ACL 2026 Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robots CVPR 2026 Towards Multiple Missing Values-resistant Unsupervised Graph Anomaly Detection AAAI 2026 Towards Persistence: Learning Topological Constraints for Event-based Small Object Detection CVPR 2026 Towards Privacy-Protected Generalized Gaze Estimation Using Diffusion Models and Domain Stability Adaptation Framework AAAI 2026 Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors CVPR 2026 Towards Robust Evaluation of Visual Activity Recognition: Resolving Verb Ambiguity with Sense Clustering EACL 2026