Computer Vision

Situational Scene Graph for Structured Human-Centric Situation Understanding WACV 2025 SOGS: Second-Order Anchor for Advanced 3D Gaussian Splatting CVPR 2025 SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods ACL 2025 Street Gaussians without 3D Object Tracker ICCV 2025 Structure-Aware Correspondence Learning for Relative Pose Estimation CVPR 2025 Structure Matters: Revisiting Boundary Refinement in Video Object Segmentation ICCV 2025 SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints AAAI 2025 SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning ICCV 2025 Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation CVPR 2025 Synthetic Video Enhances Physical Fidelity in Video Synthesis ICCV 2025 Task-Specific Information Decomposition for End-to-End Dense Video Captioning ACL 2025 Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News Detection AAAI 2025 The Art of Deception: Color Visual Illusions and Diffusion Models CVPR 2025 The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning ICCV 2025 ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration ICCV 2025 TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation CVPR 2025 Towards Continual Universal Segmentation CVPR 2025 Towards Explainable and Unprecedented Accuracy in Matching Challenging Finger Crease Patterns CVPR 2025 Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition CVPR 2025 Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion CVPR 2025 Towards Universal AI-Generated Image Detection by Variational Information Bottleneck Network CVPR 2025 Tracking objects that change in appearance with phase synchrony ICLR 2025 Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better CVPR 2025 Training Consistent Mixture-of-Experts-Based Prompt Generator for Continual Learning AAAI 2025 Training High Performance Spiking Neural Network by Temporal Model Calibration ICML 2025