Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
研究通过检测笑声来索引日常生活中的积极时刻,利用LaughAnchor系统帮助用户记录、回顾和反思这些时刻,从而支持正面经历的重构与反思。
研究通过检测笑声来索引日常生活中的积极时刻,利用LaughAnchor系统帮助用户记录、回顾和反思这些时刻,从而支持正面经历的重构与反思。
本文提出VESTA,一种无训练的长视频代理,通过策略引导的多策略检索解决证据获取问题,提高视频理解准确性。
This work addresses the challenge of constructing a persistent, autonomously updatable, and geometrically verifiable world model for long-term service robots operating in unknown environments—a task hindered by error accumulation, static scene representations, and insufficient 3D geometric evidence in existing approaches. The authors propose a baseline-increment decoupled active graph framework that separates stable static structures from revisable dynamic objects, building a structural baseline through autonomous exploration and performing uncertainty-aware verification via hierarchical object beliefs. A novel reliability-weighted state representation and a geometry-aware visibility gating mechanism are introduced to jointly inform graph-conditioned viewpoint planning, effectively mitigating erroneous deletions under occlusion and enhancing object identity continuity and event recall. Experiments demonstrate significant improvements over baselines in multi-environment simulations, with superior performance in static-object F1 scores, identity continuity, and event recall, and successful integration with onboard systems is validated on a physical robot.
This work addresses the poor physical feasibility and inefficient high-dimensional optimization inherent in black-box physical adversarial attacks for remote sensing object detection by proposing ColorFD, a novel method that employs solid-color patches as physical perturbations. ColorFD jointly optimizes patch location and color via differential evolution, significantly reducing the search space through an innovative integration of finite-difference-guided critical region localization and class-level spatial priors. Furthermore, it introduces a target-aware fitness mechanism to enhance both attack specificity and transferability. Experimental results demonstrate that ColorFD consistently outperforms existing black-box approaches across YOLOv3u, YOLOv5u, and Faster R-CNN detectors, achieving performance close to white-box baselines, with digital-domain optimizations effectively transferring to real-world imaging conditions.
This work addresses the challenge of performing precise local inpainting and deterministic editing on pre-trained 3D Gaussian splatting assets. To unify these operations, we introduce a spatial incremental layer mechanism that formulates both tasks as composite spatial increment processes: local inpainting is achieved by augmenting Gaussian primitives, while deterministic editing employs an Erase-Insert Factorization (EIF) strategy. Our approach enables lightweight, verifiable, and accurate localized maintenance of 3D Gaussian representations for the first time. Experiments demonstrate that local inpainting improves PSNR by up to 7.91 dB in target regions, and deterministic editing achieves an average PSNR of 21.97 dB in regions of interest (a gain of +11.05 dB), with public test cases yielding a Target-mask PSNR of 33.17 dB and a Target-delta correlation coefficient of 0.994.
研究通过检测笑声来索引日常生活中的积极时刻,利用LaughAnchor系统帮助用户记录、回顾和反思这些时刻,从而支持正面经历的重构与反思。
本文提出VESTA,一种无训练的长视频代理,通过策略引导的多策略检索解决证据获取问题,提高视频理解准确性。
This work addresses the challenge of constructing a persistent, autonomously updatable, and geometrically verifiable world model for long-term service robots operating in unknown environments—a task hindered by error accumulation, static scene representations, and insufficient 3D geometric evidence in existing approaches. The authors propose a baseline-increment decoupled active graph framework that separates stable static structures from revisable dynamic objects, building a structural baseline through autonomous exploration and performing uncertainty-aware verification via hierarchical object beliefs. A novel reliability-weighted state representation and a geometry-aware visibility gating mechanism are introduced to jointly inform graph-conditioned viewpoint planning, effectively mitigating erroneous deletions under occlusion and enhancing object identity continuity and event recall. Experiments demonstrate significant improvements over baselines in multi-environment simulations, with superior performance in static-object F1 scores, identity continuity, and event recall, and successful integration with onboard systems is validated on a physical robot.
This work addresses the poor physical feasibility and inefficient high-dimensional optimization inherent in black-box physical adversarial attacks for remote sensing object detection by proposing ColorFD, a novel method that employs solid-color patches as physical perturbations. ColorFD jointly optimizes patch location and color via differential evolution, significantly reducing the search space through an innovative integration of finite-difference-guided critical region localization and class-level spatial priors. Furthermore, it introduces a target-aware fitness mechanism to enhance both attack specificity and transferability. Experimental results demonstrate that ColorFD consistently outperforms existing black-box approaches across YOLOv3u, YOLOv5u, and Faster R-CNN detectors, achieving performance close to white-box baselines, with digital-domain optimizations effectively transferring to real-world imaging conditions.
This work addresses the challenge of performing precise local inpainting and deterministic editing on pre-trained 3D Gaussian splatting assets. To unify these operations, we introduce a spatial incremental layer mechanism that formulates both tasks as composite spatial increment processes: local inpainting is achieved by augmenting Gaussian primitives, while deterministic editing employs an Erase-Insert Factorization (EIF) strategy. Our approach enables lightweight, verifiable, and accurate localized maintenance of 3D Gaussian representations for the first time. Experiments demonstrate that local inpainting improves PSNR by up to 7.91 dB in target regions, and deterministic editing achieves an average PSNR of 21.97 dB in regions of interest (a gain of +11.05 dB), with public test cases yielding a Target-mask PSNR of 33.17 dB and a Target-delta correlation coefficient of 0.994.