5561 papers
This paper presents a comparative evaluation of supervised learning and open-vocabulary vision models for post-disaster scene understanding across multiple datasets, concluding that while foundation models offer flexibility, supervised training remains the most reliable approach for accurately detecting small objects and delineating boundaries in cluttered disaster scenes when annotations are available.
The paper proposes NVB-Face, a novel one-stage framework that directly generates consistent, high-quality novel-view face images from a single degraded (blind) input by extracting features and transforming them into 3D-aware latent representations via a diffusion model, thereby outperforming traditional two-stage restoration-and-synthesis pipelines.
The paper proposes Perspective-Equivariant Fine-tuning for Demosaicing (PEFD), a novel framework that enables high-fidelity, ground-truth-free multispectral image reconstruction by leveraging projective geometry and adapting pretrained foundation models to outperform existing methods on real-world datasets.
MixerCSeg is an efficient, state-of-the-art architecture for crack segmentation that integrates CNN-like local texture analysis, Transformer-style global dependency modeling, and Mamba-inspired sequential context processing within a unified encoder, enhanced by specialized edge-aware and multi-scale fusion modules to achieve high performance with minimal computational cost.
The paper proposes TIMI, a training-free framework that achieves high spatial fidelity in image-to-3D multi-instance generation by leveraging pre-trained model priors through an Instance-aware Separation Guidance module for disentanglement and a Spatial-stabilized Geometry-adaptive Update module for geometric preservation, outperforming existing methods without additional training overhead.
This paper proposes AOT, a training-free method that optimizes token reduction in Video Large Language Models by establishing local and global token anchors and aggregating informative contexts via optimal transport to efficiently eliminate redundancy while preserving spatiotemporal fidelity.
UniTalking is a unified, end-to-end diffusion framework that leverages Multi-Modal Transformer Blocks and pre-trained video priors to generate high-fidelity, lip-synchronized talking portraits with personalized voice cloning, achieving superior performance over existing open-source methods.
The paper introduces SeaVIS, the first online framework for audio-visual instance segmentation that utilizes Causal Cross Attention Fusion and Audio-Guided Contrastive Learning to effectively track and segment sounding objects in continuous video streams while suppressing silent instances.
This paper introduces LinkVLA, a novel Vision-Language-Action model for autonomous driving that unifies language and action tokens in a shared codebook, incorporates an auxiliary action understanding objective for bidirectional semantic alignment, and employs a coarse-to-fine generation strategy to significantly improve instruction following, driving performance, and inference efficiency.
This paper demonstrates that the effectiveness of global token mixing in MRI restoration is highly task-dependent, showing that while local gated CNNs suffice for reconstruction and super-resolution tasks constrained by physics or preserved low-frequency data, global models are superior for denoising tasks involving spatially heteroscedastic noise.
This paper introduces the Deepfake Forensics Adapter (DFA), a novel dual-stream framework that integrates a frozen CLIP model with global and local forensic analysis streams to achieve state-of-the-art generalization in deepfake detection, particularly demonstrating significant performance improvements on the challenging DFDC dataset.
The paper introduces VidDoS, the first universal Energy-Latency Attack framework for Video-LLMs that employs masked teacher forcing and refusal penalties to generate instance-agnostic triggers, causing extreme token expansion and inference latency that lead to critical safety violations in real-time applications.
This paper introduces MM-Mem, a cognition-inspired pyramidal multimodal memory architecture that leverages Fuzzy-Trace Theory and a Semantic Information Bottleneck to progressively distill verbatim visual details into abstract semantic schemas, thereby enabling efficient long-horizon video understanding through hierarchical storage and entropy-driven retrieval.
To address the limitations of existing sequential models in handling noisy echocardiography probe trajectories, this paper proposes UltraStar, a semantic-aware star graph framework that reformulates navigation as anchor-based global localization by connecting the current view directly to representative historical keyframes, thereby achieving robust performance and better scalability on large-scale datasets.
This paper introduces WildCross, a large-scale cross-modal benchmark featuring over 476K annotated RGB frames and synchronized lidar data designed to advance place recognition and metric depth estimation in unstructured natural environments where existing urban-focused datasets fall short.
This paper presents SCATR, a novel LiDAR-based tracking-by-attention framework that mitigates new instance suppression and bridges the performance gap with detection-based methods through two architecture-agnostic training strategies: Second Chance Assignment and Track Query Dropout, achieving state-of-the-art results on the nuScenes benchmark.
The paper proposes ATA, a novel training-free, plug-and-play framework that enhances Vision-Language-Action models by introducing implicit reasoning through complementary attention-guided and action-guided strategies, thereby improving task success and robustness without the need for additional annotations or retraining.
This paper introduces RadioGS, a novel inverse rendering framework that leverages a radiometric consistency constraint and Gaussian surfels to accurately disentangle material properties from complex global illumination effects, enabling efficient relighting and superior performance over existing Gaussian-based methods.
This paper introduces PhotoBench, the first benchmark constructed from authentic personal albums to shift photo retrieval from simple visual matching to complex, intent-driven reasoning by exposing critical limitations in current unified embedding and agentic systems regarding non-visual constraints and multi-source fusion.
This paper introduces a rate-distortion-theoretic framework that characterizes the generalization trade-offs of human and machine vision systems using geometric signatures of slope and curvature, revealing that while both follow a common lossy-compression principle, humans exhibit smoother and more flexible trade-offs compared to the steeper, more brittle regimes of modern deep networks.