Computer Vision – ECCV 2024

Rethinking Data Bias: Dataset Copyright Protection via Embedding Class-wise Hidden Bias.- Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularization.- SILC: Improving Vision Language Pretraining with Self-Distillation.- Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction.- Leveraging temporal contextualization for video action recognition.- ChEX: Interactive Localization and Region Description in Chest X-rays.- AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale.- CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts.- ZigMa: A DiT-style Zigzag Mamba Diffusion Model.- EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion.- On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines.- HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization.- Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time.- Safe-Sim: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries.- Analysis-by-Synthesis Transformer for Single-View 3D Reconstruction.- Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning.- WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians.- SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference.- Flying with Photons: Rendering Novel Views of Propagating Light.- RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos.- MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images.- 3DGazeNet: Generalizing Gaze Estimation with Weak Supervision from Synthetic Views.- Removing Distributional Discrepancies in Captions Improves Image-Text Alignment.- Resilience of Entropy Model in Distributed Neural Networks.- Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis.- Implicit Concept Removal of Diffusion Models.- PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discovery.