8926 papers
This paper proposes a Structure-to-Image paradigm for zero-shot colonoscopic depth estimation that leverages phase congruency and cross-level structure constraints to bridge the sim-to-real domain gap, achieving a 44.18% reduction in RMSE compared to existing methods.
LiREC-Net is a target-free, learning-based network that unifies the calibration of LiDAR, RGB, and event sensors within a single framework by leveraging a shared LiDAR representation to achieve high-accuracy multi-sensor alignment in natural driving scenes.
This paper proposes a hybrid data-pipeline parallelism framework that leverages conditional guidance scheduling and adaptive parallelism switching to significantly accelerate diffusion model inference while preserving generation quality across various architectures.
This paper proposes SAPNet++, a novel framework for point-prompted instance segmentation that addresses granularity ambiguity and boundary uncertainty through semantic-aware proposal selection (S-MIL) and multi-level affinity refinement, significantly improving segmentation performance across four challenging datasets.
This paper introduces CUPID, a novel unlearning framework that addresses the "shortcut unlearning" phenomenon—where models struggle to forget bias-aligned samples by instead unlearning the bias itself—by partitioning data based on loss landscape sharpness and disentangling model parameters to perform targeted updates that effectively mitigate unintended biases.
This paper introduces Forensic Answer-Questioning (FAQ), a large-scale benchmark and corresponding instruction-tuning set designed to enhance Vision-Language Models' ability to detect video deepfakes by evaluating and improving their temporal reasoning capabilities across three hierarchical levels: facial perception, temporal grounding, and forensic reasoning.
XStreamVGGT is a tuning-free, memory-efficient streaming 3D reconstruction method that combines token pruning and dimension-adaptive quantization to compress the Key-Value cache, achieving significant reductions in memory usage and inference latency while maintaining high accuracy for long-horizon applications.
GeoMotion proposes a fully learning-based, end-to-end feed-forward approach for motion segmentation that leverages latent 4D geometry and attention mechanisms to implicitly disentangle object and camera motion, thereby achieving state-of-the-art performance with high efficiency by eliminating the need for noisy explicit correspondence estimation and iterative optimization.
This paper introduces StoryMovie, a dataset of 1,757 visual stories aligned with movie scripts and subtitles via LCS matching, which is used to fine-tune the Qwen Storyteller3 model to significantly improve semantic alignment and dialogue attribution accuracy compared to models relying solely on visual grounding.
This paper proposes Meta-FC, a novel meta-learning framework that enhances the robustness and generalizability of deep learning-based watermarking by addressing the optimization conflicts of single-random-distortion training through feature consistency constraints and meta-training tasks designed to identify distortion-invariant representations.
This paper proposes Learning-to-Re-Prompt (L2RP), a cost-aware framework that analyzes annotation error propagation in endoscopic video segmentation and dynamically learns an adaptive policy to optimize the trade-off between expert intervention effort and segmentation accuracy for Barrett's esophagus dysplasia.
The paper proposes DynamicGTR, a framework that enhances Vision-Language Models' zero-shot graph question-answering performance by dynamically selecting the optimal graph topology representation for each query, thereby improving accuracy and efficiency while demonstrating strong transferability across tasks and domains without additional training.
The paper proposes GFPL, a novel framework that leverages Gaussian Mixture Model-based prototype generation and Bhattacharyya distance aggregation to effectively address data imbalance and reduce communication overhead in resource-constrained federated learning scenarios.
This paper presents a UNet-based neural network trained on a large custom-labeled dataset to achieve accurate, real-time 3D cone localization and color prediction, demonstrating superior performance over traditional methods and validating its effectiveness in end-to-end autonomous racing systems.
This paper introduces NESS, a continual learning method that mitigates catastrophic forgetting by constraining task-specific updates to an approximate null space derived from the smallest singular values of input representations, thereby enabling efficient adaptation while preserving performance on previous tasks.
This paper introduces "geometry-as-context," an autoregressive framework that iteratively estimates scene geometry and restores novel views to achieve superior scene consistency and camera control in video generation, overcoming the error accumulation and non-differentiability issues of previous methods.
The paper presents CARD-ViT, a self-supervised Vision Transformer framework trained exclusively on ECG-gated CT data that successfully enables automated Coronary Artery Calcium scoring on non-gated scans, thereby facilitating scalable cardiovascular risk assessment using routine chest imaging without requiring additional scans or annotations.
This paper proposes Directed Ordinal Diffusion Regularization (D-ODR), a novel method that enforces the unidirectional nature of diabetic retinopathy progression through a directed graph and multi-scale diffusion, thereby preventing biologically implausible reverse transitions and achieving superior grading performance compared to existing state-of-the-art approaches.
This paper presents a lightweight, mobile-optimized deep learning framework using MobileNetV3 with a Consistent Rank Logits head to efficiently and accurately assess diabetic retinopathy severity from fundus images, achieving a Quadratic Weighted Kappa score of 0.9019 to enable scalable early-stage screening.
This paper proposes MVGFDR, an end-to-end multi-view graph fusion framework that explicitly disentangles shared and view-specific features through graph initialization, frequency-domain fusion, and masked cross-view reconstruction to achieve superior diabetic retinopathy grading on multi-view fundus images.