2786 papers
SurgCUT3R is a novel framework that addresses the challenges of data scarcity and pose drift in monocular endoscopic video reconstruction by leveraging a synthetic data generation pipeline, hybrid supervision, and a hierarchical inference strategy to achieve robust, accurate, and efficient 3D surgical scene understanding.
This paper introduces Conditional Unbalanced Optimal Transport Maps (CUOTM), a robust conditional generative framework that mitigates the outlier sensitivity of classical Conditional Optimal Transport by relaxing distribution-matching constraints via Csiszár divergence penalties while preserving conditioning marginals through a theoretically justified triangular -transform parameterization.
The paper proposes T2SGrid, a novel framework that reformulates video temporal grounding as a spatial understanding task by arranging video frames into composite grid images via overlapping sliding windows, thereby overcoming the limitations of existing temporal encoding methods and achieving superior performance on standard benchmarks.
This paper proposes a novel approach to image-based shape retrieval that leverages pre-aligned multi-modal encoders and a hard contrastive learning loss to achieve state-of-the-art performance in both zero-shot and supervised settings, eliminating the need for explicit view-based supervision or view synthesis.
This paper proposes a perception-aware multimodal reasoning framework that enhances Vision-Language Models' spatial understanding in monocular driving scenarios by representing objects with Visual Reference Tokens and utilizing a Multimodal Chain-of-Thought dataset, achieving significant performance gains on the SURDS benchmark through standard supervised fine-tuning.
This paper introduces ADAS-TO, the first large-scale naturalistic multimodal dataset of 15,659 ADAS-to-manual takeover events from 327 drivers, which combines kinematic and vision-language analysis to characterize safety-critical scenarios and demonstrate that actionable visual cues often precede takeovers by over three seconds.
MipSLAM is a novel 3D Gaussian Splatting SLAM framework that achieves high-fidelity anti-aliased rendering and robust pose estimation by integrating an Elliptical Adaptive Anti-aliasing algorithm, a Spectral-Aware Pose Graph Optimization module, and a local frequency-domain perceptual loss to overcome aliasing artifacts and trajectory drift.
AdaGen introduces a general, learnable framework that employs reinforcement learning with an adversarial reward to dynamically adapt step-specific parameters during iterative image synthesis, thereby overcoming the limitations of static, manually-designed schedules and achieving superior performance across diverse generative models with reduced inference costs.
TrajPred is a novel framework that enhances surgical instrument-tissue interaction recognition in vision-language models by encoding instrument trajectories to capture temporal motion cues and generating fine-grained visual semantic embeddings, thereby significantly improving performance and vision-text alignment on the CholecT50 benchmark.
This paper presents OV-DEIM, a real-time end-to-end DETR-style open-vocabulary object detector that combines the DEIMv2 framework with a query supplement strategy and a novel GridSynthetic data augmentation technique to achieve state-of-the-art performance and efficiency, particularly for rare categories.
This paper introduces TFM, a temporal attack framework that exploits the vulnerability of text-to-video models to generate harmful content by providing only sparse boundary conditions (start and end frames) and implicitly substituting sensitive cues, thereby bypassing existing safety filters and significantly increasing jailbreak success rates.
This paper proposes a novel fine-grained 3D facial reconstruction method for micro-expressions that integrates global dynamic features with locally-enriched cues from 2D motions, facial priors, and 3D geometry to overcome data scarcity and achieve superior geometric accuracy and perceptual detail compared to state-of-the-art approaches.
This paper proposes CAPL, a framework that mitigates multi-image hallucinations in large vision-language models by introducing a selectable image token interaction mechanism for fine-grained cross-image alignment and a preference learning strategy that trains the model to rely on genuine visual evidence rather than textual priors.
SODA introduces a sensitivity-oriented dynamic acceleration framework for Diffusion Transformers that adaptively optimizes caching and pruning strategies through fine-grained sensitivity modeling and dynamic programming, achieving state-of-the-art generation fidelity under controllable acceleration ratios.
MedSteer is a training-free activation-steering framework that generates structurally preserved counterfactual endoscopic images by manipulating cross-attention activations in diffusion transformers, outperforming existing methods in concept editing and downstream medical detection tasks.
This paper introduces VirtueBench, a new benchmark designed to evaluate the trustworthiness of Vision-Language Models in long video understanding by distinguishing between answerable and unanswerable cases to prevent misleading accuracy scores caused by guessing under uncertainty.
This paper introduces PhyVLM-CR, a novel unified framework that integrates Vision-Language Model semantic priors with physical scattering parameters to seamlessly remove both thin and thick clouds from optical remote sensing imagery without explicit cloud-type segmentation, thereby achieving high-fidelity, hallucination-free surface reconstruction.
This paper proposes PSG-UIENet, a novel underwater image enhancement network that integrates Retinex-based illumination correction with CLIP-derived textual semantics to overcome the limitations of existing methods, supported by the introduction of a new large-scale image-text dataset (LUIQD-TD) and a specialized semantic similarity loss function.
This paper introduces a novel framework for EEG-based visual decoding that aligns brain signals with intermediate visual layers via a proposed "Neural Visibility" concept and a Hierarchically Complementary Fusion mechanism, achieving state-of-the-art performance by significantly reducing cross-modal information mismatch.
The paper introduces mAVE, a novel watermarking framework that cryptographically binds audio and video latents in joint generation models to eliminate the "Binding Vulnerability" of existing methods and robustly defend against adversarial Swap Attacks without requiring model fine-tuning.