3922 papers
This paper introduces a point-supervised framework for skeleton-based human action segmentation that leverages multimodal features and a novel pseudo-labeling strategy to achieve competitive performance with significantly reduced annotation costs compared to fully-supervised methods.
VG3S is a novel framework that enhances 3D semantic occupancy prediction for autonomous driving by integrating strong geometric priors from frozen Vision Foundation Models into Gaussian splatting via a hierarchical feature adapter, achieving significant performance gains on the nuScenes benchmark.
The paper introduces CoE, a training-free multimodal summarization framework that leverages a Hierarchical Event Graph to guide a Chain-of-Events reasoning process, effectively addressing limitations in cross-modal grounding and temporal modeling while achieving state-of-the-art performance across diverse datasets.
The paper introduces EntON, a novel 3D Gaussian Splatting method that employs an Eigenentropy-aware alternating densification strategy to simultaneously improve geometric accuracy and rendering quality while significantly reducing the number of Gaussians and training time.
This paper introduces Word-Anchored Temporal Forgery Localization (WAFL), a novel paradigm that shifts forgery detection from continuous regression to discrete word-level classification by aligning with linguistic boundaries, employing a forensic feature realignment module for efficient feature mapping, and utilizing an artifact-centric asymmetric loss to overcome class imbalance, thereby achieving superior localization performance with significantly reduced computational costs.
This paper introduces Spatially-Sparse Linear Attention (SSLA) and its application in the SSLA-Det model, an end-to-end asynchronous framework for event-based object detection that achieves state-of-the-art accuracy while significantly reducing per-event computation by leveraging state-level sparsity and parallel training.
TaPD is a unified, plug-and-play framework that employs temporal-adaptive progressive distillation and a temporal backfilling module to enable robust trajectory forecasting under variable and extremely short observation histories by transferring knowledge from long-horizon teachers and reconstructing missing past context.
DC-Merge is a novel model merging method that achieves state-of-the-art performance by first balancing the energy distribution of task vectors through singular value smoothing and then aligning their directional geometries via projection onto a shared orthogonal subspace to preserve multi-task knowledge.
The paper introduces HCF-RES, a novel multi-modal framework that achieves state-of-the-art performance in 3D Generalized Referring Expression Segmentation by leveraging hierarchical visual semantic decomposition with SAM and CLIP, alongside progressive multi-level fusion to effectively integrate 2D semantic and 3D geometric features.
NOVA introduces a novel 3D multi-object tracking framework that leverages large language models to reformulate tracking as an autoregressive next-step sequence completion task, enabling superior open-vocabulary generalization and identity consistency through spatio-temporal semantic modeling without relying on closed-set assumptions.
GazeMoE is a novel end-to-end framework that leverages Mixture-of-Experts modules to adaptively fuse multi-modal cues from a frozen vision foundation model, achieving state-of-the-art performance in human gaze target estimation by addressing class imbalance and enhancing robustness through specialized loss functions and data augmentation.
This paper presents ODD-SEC, a real-time onboard drone detection system for moving carriers that utilizes a spinning event camera and a novel motion-compensation-free representation to achieve 360-degree surveillance with high accuracy under challenging conditions.
HiPP-Prune is a hierarchical preference-conditioned structured pruning framework for vision-language models that leverages visual sensitivity signals and multi-objective Group Relative Policy Optimization to generate controllable pruning plans, effectively balancing task utility, compression, and hallucination robustness.
The paper proposes StrSR, a novel one-step adversarial distillation framework that employs asymmetric discriminative distillation and frequency distribution matching to overcome trajectory mismatches and periodic artifacts, thereby achieving state-of-the-art performance in real-world image super-resolution using Diffusion Transformers.
This paper introduces OccNL, the first benchmark for 3D semantic occupancy prediction under label noise, and proposes DPR-Occ, a novel framework that leverages dual-source partial label reasoning to achieve robust performance and prevent catastrophic collapse in noisy 3D voxel spaces where existing 2D noise-robust strategies fail.
This paper proposes ADiVA, a generative zero-shot learning framework that addresses the class-instance and semantic-visual domain gaps by jointly modeling attribute distributions to capture instance-specific variability and employing visual-guided alignment to refine semantic representations, thereby significantly outperforming state-of-the-art methods on benchmark datasets.
FlowMotion is a novel training-free framework that achieves efficient and flexible video motion transfer by directly leveraging early latent predictions from flow-based text-to-video models to extract motion representations and align patterns, while employing velocity regularization to ensure smooth motion evolution.
This paper proposes a novel 3D dental implant inpainting method using perpendicular score-based diffusion models that operate in the projection domain to capture inter-projection correlations, thereby generating high-quality, artifact-reduced CBCT images with improved consistency compared to existing 2D-based approaches.
The paper introduces DEX-AR, a novel dynamic explainability method that generates per-token and sequence-level heatmaps for autoregressive Vision-Language Models by computing layer-wise gradients and employing dynamic filtering to distinguish visually-grounded from linguistic tokens, thereby improving interpretability and performance across multiple benchmarks.
The paper proposes LTA, a transfer-based adversarial attack that optimizes perturbations within the latent space of a pretrained Stable Diffusion VAE to generate spatially coherent, low-frequency examples that achieve superior transferability and robustness against common preprocessing compared to traditional pixel-space methods.