3744 papers
This paper proposes SSL-SLR, a self-supervised learning framework for sign language recognition that addresses the limitations of standard contrastive methods by introducing free-negative pairs and a novel data augmentation technique to better handle video redundancy and shared movements, thereby achieving significant accuracy improvements across various evaluation settings.
This paper introduces RED, a robust event-guided motion deblurring network that employs a robustness-oriented perturbation strategy and a modality-specific disentanglement mechanism to effectively reconstruct sharp images from fragmented event data caused by real-world sensor under-reporting.
This paper introduces Kernel VICReg, a novel self-supervised learning framework that extends the VICReg objective into a Reproducing Kernel Hilbert Space to capture nonlinear dependencies and improve representation learning performance on datasets with complex geometric structures.
This paper proposes C²Prompt, a novel federated continual learning method that mitigates temporal and spatial forgetting by introducing a local class distribution compensation mechanism and a class-aware prompt aggregation scheme to enhance class-wise knowledge coherence across distributed clients.
This paper presents a vision-based framework for legged robots that enables robust decision-driven semantic exploration by integrating confidence-calibrated perception, controlled-growth topological memory, and utility-driven subgoal selection to overcome the limitations of conventional geometry-centric navigation in open-world environments.
DeCLIP is a replay-free, parameter-efficient framework for Multi-Label Class-Incremental Learning that decouples CLIP representations through class-specific prompting and Adaptive Similarity Tempering to effectively mitigate catastrophic forgetting and reduce false-positive rates without violating CLIP's single image-text alignment paradigm.
The paper introduces BOUND, an open-world object detector that advances beyond simple "unknown" labeling by inferring coarse-grained, hierarchical categories for unseen objects to enable more informed decision-making while maintaining high performance on known classes.
The paper introduces LikePhys, a training-free evaluation method using likelihood preferences to assess intuitive physics understanding in video diffusion models, demonstrating that current models show improving capabilities in physical reasoning as they scale despite challenges with complex dynamics.
CanvasMAR enhances masked autoregressive video prediction by introducing a global "canvas" prior and a motion-aware curriculum to generate high-fidelity, coherent videos with fewer sampling steps, achieving performance that rivals advanced diffusion-based methods.
The paper introduces 3DThinker, a novel framework that enables vision-language models to perform 3D spatial reasoning from limited views by aligning their internal representations with a 3D foundation model and refining the reasoning process through outcome-based optimization, all without requiring explicit 3D prior inputs or labeled 3D training data.
This paper introduces AURASeg, an attention-guided segmentation framework featuring a Residual Boundary Refinement Module and an Attention Progressive Upsampling Decoder to enhance drivable-area boundary precision and multi-scale feature representation for onboard robot navigation, demonstrating superior performance on multiple datasets and successful deployment on a Jetson Nano.
This paper introduces CULTIVate, a comprehensive benchmark and evaluation framework designed to assess the cultural faithfulness of text-to-image models in depicting social activities across 16 countries, revealing significant performance disparities between Global North and South regions and demonstrating that its proposed metrics align more closely with human judgment than existing standards.
This paper proposes a dual-mechanism collaborative optimization framework that synergistically integrates structural fairness decoupling and global distribution alignment to enhance both inter-group and intra-group fairness in deepfake detection without compromising overall accuracy.
LaxMotion is a novel framework for 3D human motion generation that replaces precise 3D coordinate supervision with a relaxed paradigm based on global trajectories and monocular 2D cues, thereby enhancing model generalization and diversity while achieving performance comparable to fully supervised methods.
This paper introduces the Cultural Reference Transformation (CRT) metric to evaluate how diffusion models navigate the tension between memorization and generalization in culturally iconic contexts, revealing that model behavior depends on distinct recognition and realization mechanisms influenced by factors like data frequency, textual uniqueness, and reference popularity.
This paper presents Co-Layout, a novel framework that integrates large language models with grid-based integer programming and a coarse-to-fine optimization strategy to jointly optimize room layouts and furniture placement, significantly outperforming existing two-stage pipelines in both solution quality and computational efficiency.
This paper introduces SPARK, a jailbreak framework that exploits cross-modal associations in text-to-video models by combining neutral scene anchors, latent auditory triggers, and stylistic modulators to generate semantically unsafe videos that bypass safety guardrails while maintaining a benign appearance.
The paper introduces MRIQT, a physics-aware 3D conditional diffusion model that significantly enhances the image quality and diagnostic fidelity of portable ultra-low-field neonatal MRI by translating noisy scans into high-fidelity images comparable to high-field MRI.
The paper introduces FunnyNodules, a fully parameterized synthetic dataset of lung nodule-like shapes with controllable visual attributes and known decision rules, designed to systematically evaluate and benchmark explainable AI models by verifying whether they learn correct attribute-target relations and align their attention with relevant diagnostic features.
The paper introduces FireScope, a novel VLM-based framework and accompanying FireScope-Bench dataset that leverage chain-of-thought reasoning to significantly improve the generalization, interpretability, and accuracy of cross-continental wildfire risk prediction by integrating visual, climatic, and geographic factors.