Recommender systems remain organized around passive preference inference: estimate latent interest from behavioral traces, then rank. Past: implicit feedback, matrix factorization, learning-to-rank, and large-scale offline evaluation made this abstraction highly productive. Present: four mismatches expose what predicti...
Kai-Wen Deng, Hao Jiang, Jia-Xin Cheng et al.· Proceedings of the 20th ACM...· 0 citations
Recommender systems remain organized around passive preference inference: estimate latent interest from behavioral traces, then rank. Past: implicit feedback, matrix factorization, learning-to-rank, and large-scale offline evaluation made this abstraction highly productive. Present: four mismatches expose what predicti...
Kai-Wen Deng, Hao Jiang, Jia-Xin Cheng et al.· Proceedings of the 20th ACM...· 0 citations
Under a strict cross-dataset zero-shot protocol on five IAD benchmarks, MOPDA outperforms the evaluated LVLM-based baselines on most detection, localization, and judgment metrics while remaining competitive with CLIP-based methods.
This work proposes a novel attention-free integrated spatiotemporal architecture named Integrated Mamba-HyperGCN (Pose Magic++), which significantly improves the estimation accuracy of peripheral joints without incurring extra computational cost.
Xin-Yi Zhang, Qi-Qi Bao, Wen-Ming Yang et al.· ACM Transactions on Multimed...· 0 citations
VIVAS is proposed, a framework built upon the unified token space paradigm, which introduces a dense-structural-semantic vision tokenizer, which expands the textual vocabulary into a unified vision-language vocabulary by incorporating a visual vocabulary.
Zhe-Han Kan, Yu-Bo Zhu, Xing-Hua Jiang et al.· 1 citation
UVU effectively synergizes pixel-level visual perception with semantic-level visual understanding, internalizing visual reconstruction capabilities and unlocking the facilitative role of visual supervision in enhancing understanding in the pre-training stage.
Zhe-Han Kan, Xing-Hua Jiang, Yu-Bo Zhu et al.· 1 citation
CoverPrune is introduced, a training-free framework that formulates inference-time token pruning as an Optimal Transport (OT) problem, and the Feature-Spatial-Temporal (FST) transport cost and target capacity, along with an efficient Spatial-Guided Greedy Selection (SGS) algorithm to approximate the OT objective.
Peng Ling, Ying-Da Yin, Ling-Ting Zhu et al.· 0 citations
EffectLearner is proposed, a semantic-reasoning-enhanced framework that combines a VLM-based Object-Effect Reasoner with a DiT-based Video Eraser that achieves clear advantages on both EffectWorld-Eval and the challenging EffectWorld-Wild, demonstrating its ability to deliver high-quality video object removal in comple...
Large vision-language models (LVLMs) have recently shown strong potential for industrial anomaly detection (IAD) by providing image-level anomaly judgments and interpretable defect reasoning. However, current LVLM-based IAD methods still struggle to produce precise pixel-level anomaly maps from generated language judgm...
Shuimu Chen, Jing Jin, Nan Su et al.· arXiv.org· 1 citation
LoTA-N2N demonstrates that estimated local interaction and spatial cancellation control provide effective design principles for single-image self-supervised denoising without paired clean targets, repeated acquisitions, or a predefined re-corruption model.
Jintong Hu, Bin Xia, Jun-Lin Liu et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
