Audio-visual segmentation via unlabeled frame exploitation

Turnitin 降AI改写 早检测系统 早降重系统 Turnitin-UK版 万方检测-期刊版 维普编辑部版 Grammarly检测 Paperpass检测 checkpass检测 PaperYY检测
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Turbo: Informativity-driven acceleration plug-in for vision-language large models

C Ju, H Wang, H Cheng, X Chen, Z Zhai… - … on Computer Vision, 2024 - Springer
Abstract Vision-Language Large Models (VLMs) recently become primary backbone of AI,
due to the impressive performance. However, their expensive computation costs, ie …
Uložiť Citovať Citované 5-krát Súvisiace články Všetky verzie 8
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Video-guided foley sound generation with multimodal controls

Z Chen, P Seetharaman, B Russell, O Nieto… - arxiv preprint arxiv …, 2024 - arxiv.org
Generating sound effects for videos often requires creating artistic sound effects that diverge
significantly from real-life sources and flexible control in the sound design. To address this …
Uložiť Citovať Citované 3-krát Súvisiace články Všetky verzie 2 HTML verzia
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Denoiser: Rethinking the robustness for open-vocabulary action recognition

H Cheng, C Ju, H Wang, J Liu, M Chen, Q Hu… - arxiv preprint arxiv …, 2024 - arxiv.org
As one of the fundamental video tasks in computer vision, Open-Vocabulary Action
Recognition (OVAR) recently gains increasing attention, with the development of vision …
Uložiť Citovať Citované 5-krát Súvisiace články Všetky verzie 4 HTML verzia
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training

H Wang, C Ju, W Lin, S **ao, M Chen, Y Huang… - arxiv preprint arxiv …, 2024 - arxiv.org
In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-
training (CLIP) has made significant strides, becoming foundation for various downstream …
Uložiť Citovať Citované 2-krát Súvisiace články Všetky verzie 2 HTML verzia
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Contrast-Unity for Partially-Supervised Temporal Sentence Grounding

H Wang, C Ju, W Lin, C Ma, S **ao, Y Zhang… - arxiv preprint arxiv …, 2025 - arxiv.org
Temporal sentence grounding aims to detect event timestamps described by the natural
language query from given untrimmed videos. The existing fully-supervised setting achieves …
Uložiť Citovať Súvisiace články Všetky verzie 2 HTML verzia
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance

H Wang, Z Yu, G Spadaro, C Ju, V Quétu… - arxiv preprint arxiv …, 2025 - arxiv.org
Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable
effectiveness for multi-modal tasks due to their abilities to generate and understand cross …
Uložiť Citovať Súvisiace články Všetky verzie 2 HTML verzia