Results 141 to 150 of about 10,385 (175)

Learning Comprehensive Visual Grounding for Video Captioning

IEEE transactions on circuits and systems for video technology (Print)
The grounding accuracy of existing video captioners is still behind the expectation. The majority of existing methods perform grounded video captioning on sparse entity annotations.
Wenhui Jiang, Linxin Liu, Yuming Fang, Yibo Cheng, Yuxin Peng, Yang Liu   +5 more
semanticscholar   +1 more source

PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning

arXiv.org
Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources, which hinders the ...
Lin Xu, Yilin Zhao, Daquan Zhou, Zhijie Lin, S. Ng, Jiashi Feng   +5 more
semanticscholar   +1 more source

Action-aware Linguistic Skeleton Optimization Network for Non-autoregressive Video Captioning

ACM Trans. Multim. Comput. Commun. Appl.
Non-autoregressive video captioning methods generate visual words in parallel but often overlook semantic correlations among them, especially regarding verbs, leading to lower caption quality.
Shuqin Chen, Xian Zhong, Yi Zhang, Lei Zhu, Ping Li, Xiaokang Yang, Bin Sheng   +6 more
semanticscholar   +1 more source

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting

arXiv.org
We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects through time. CAT-V integrates three key components: a Segmenter based on
Yunlong Tang, Jing Bi, Chao Huang, Susan Liang, D. Shimada, Hang Hua, Yunzhong Xiao, Yizhi Song, Pinxin Liu, Mingqian Feng, Junjia Guo, Zhuo Liu, Luchuan Song, A. Vosoughi, Jinxi He, Liu He, Zeliang Zhang, Jiebo Luo, Chenliang Xu   +18 more
semanticscholar   +1 more source

NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative

International Conference on Learning Representations
Existing video captioning benchmarks and models lack causal-temporal narrative, which is sequences of events linked through cause and effect, unfolding over time and driven by characters or agents.
Asmar Nadeem, Faegheh Sardari, R. Dawes, Syed Sameed Husain, Adrian Hilton, A. Mustafa   +5 more
semanticscholar   +1 more source

MoS2: Mixture of Scale and Shift Experts for Text-Only Video Captioning

ACM Multimedia
Video captioning is a challenging task and typically requires paired video-text data for training. However, manually annotating coherent textual descriptions for videos is laborious and time-consuming.
Heng Jia, Yunqiu Xu, Linchao Zhu, Guang Chen, Yufei Wang, Yi Yang   +5 more
semanticscholar   +1 more source

EvCap: Element-Aware Video Captioning

IEEE transactions on circuits and systems for video technology (Print)
Video captioning is a multi-modal task across computer vision and natural language processing. Previous methods generally follow two paradigms, i.e. template-based and sequence-based. Template-based methods can generate relatively accurate elements (e.g.
Sheng Liu, Annan Li, Yuwei Zhao, Jiahao Wang, Yunhong Wang   +4 more
semanticscholar   +1 more source

RETTA: Retrieval-enhanced test-time adaptation for zero-shot video captioning

Pattern Recognition
Despite the significant progress of fully-supervised video captioning, zero-shot methods remain much less explored. In this paper, we propose a novel zero-shot video captioning framework named Retrieval-Enhanced Test-Time Adaptation (RETTA), which takes ...
Yunchuan Ma, Laiyun Qing, Guorong Li, Yuankai Qi, Amin Beheshti, Quan Z. Sheng, Qingming Huang   +6 more
semanticscholar   +1 more source

Traffic Scenario Understanding and Video Captioning via Guidance Attention Captioning Network

IEEE transactions on intelligent transportation systems (Print)
Describing a traffic scenario from the driver’s perspective is a challenging process for Advanced Driving Assistance System (ADAS), involving different sub-tasks of detection, tracking, segmentation, etc.
Chunsheng Liu, Xiao Zhang, F. Chang, Shuang Li, Penghui Hao, Yansha Lu, Yinhai Wang   +6 more
semanticscholar   +1 more source

Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning

AAAI Conference on Artificial Intelligence
Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locating the temporal location of event,
Shiping Ge, Qiang Chen, Zhiwei Jiang, Yafeng Yin, Liu Qin, Ziyao Chen, Qing Gu   +6 more
semanticscholar   +1 more source