English
Related papers

Related papers: End-to-End Dense Video Captioning with Masked Tran…

200 papers

The dynamic imbalance of the fore-background is a major challenge in video object counting, which is usually caused by the sparsity of target objects. This remains understudied in existing works and often leads to severe…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Bing Cao , Quanhao Lu , Jiekang Feng , Qilong Wang , Qinghua Hu , Pengfei Zhu

A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Tsu-Jui Fu , Linjie Li , Zhe Gan , Kevin Lin , William Yang Wang , Lijuan Wang , Zicheng Liu

Large-scale pre-trained multi-modal models (e.g., CLIP) demonstrate strong zero-shot transfer capability in many discriminative tasks. Their adaptation to zero-shot image-conditioned text generation tasks has drawn increasing interest.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Wei Li , Linchao Zhu , Longyin Wen , Yi Yang

Efficient video tokenization remains a key bottleneck in learning general purpose vision models that are capable of processing long video sequences. Prevailing approaches are restricted to encoding videos to a fixed number of tokens, where…

Machine Learning · Computer Science 2025-02-04 Wilson Yan , Volodymyr Mnih , Aleksandra Faust , Matei Zaharia , Pieter Abbeel , Hao Liu

Automatic captioning of images is a task that combines the challenges of image analysis and text generation. One important aspect in captioning is the notion of attention: How to decide what to describe and in which order. Inspired by the…

Computer Vision and Pattern Recognition · Computer Science 2020-10-06 Sen He , Wentong Liao , Hamed R. Tavakoli , Michael Yang , Bodo Rosenhahn , Nicolas Pugeault

The use of explicit object detectors as an intermediate step to image captioning - which used to constitute an essential stage in early work - is often bypassed in the currently dominant end-to-end approaches, where the language model is…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Josiah Wang , Pranava Madhyastha , Lucia Specia

Attention-based neural encoder-decoder frameworks have been widely used for image captioning. Many of these frameworks deploy their full focus on generating the caption from scratch by relying solely on the image features or the object…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Fawaz Sammani , Mahmoud Elsayed

Automatically translating images to texts involves image scene understanding and language modeling. In this paper, we propose a novel model, termed RefineCap, that refines the output vocabulary of the language decoder using decoder-guided…

Computation and Language · Computer Science 2021-09-09 Yekun Chai , Shuo Jin , Junliang Xing

Videos convey rich information. Dynamic spatio-temporal relationships between people/objects, and diverse multimodal events are present in a video clip. Hence, it is important to develop automated models that can accurately extract such…

Computation and Language · Computer Science 2020-05-14 Hyounghun Kim , Zineng Tang , Mohit Bansal

Typical techniques for video captioning follow the encoder-decoder framework, which can only focus on one source video being processed. A potential disadvantage of such design is that it cannot capture the multiple visual context…

Computer Vision and Pattern Recognition · Computer Science 2019-05-13 Wenjie Pei , Jiyuan Zhang , Xiangrong Wang , Lei Ke , Xiaoyong Shen , Yu-Wing Tai

This report describes our solution to the VALUE Challenge 2021 in the captioning task. Our solution, named CLIP4Caption++, is built on X-Linear/X-Transformer, which is an advanced model with encoder-decoder architecture. We make the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-15 Mingkang Tang , Zhanyu Wang , Zhaoyang Zeng , Fengyun Rao , Dian Li

In this paper, we introduce T-DEED, a Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in sports videos. T-DEED addresses multiple challenges in the task, including the need for discriminability among frame…

Computer Vision and Pattern Recognition · Computer Science 2024-04-12 Artur Xarles , Sergio Escalera , Thomas B. Moeslund , Albert Clapés

Although many approaches for multi-human pose estimation in videos have shown profound results, they require densely annotated data which entails excessive man labor. Furthermore, there exists occlusion and motion blur that inevitably lead…

Computer Vision and Pattern Recognition · Computer Science 2022-07-29 Kyung-Min Jin , Gun-Hee Lee , Seong-Whan Lee

End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due to the modality…

Computation and Language · Computer Science 2022-07-05 Jinming Zhao , Hao Yang , Ehsan Shareghi , Gholamreza Haffari

Recently, dense video captioning has made attractive progress in detecting and captioning all events in a long untrimmed video. Despite promising results were achieved, most existing methods do not sufficiently explore the scene evolution…

Computer Vision and Pattern Recognition · Computer Science 2025-06-26 Zhiwang Zhang , Dong Xu , Wanli Ouyang , Luping Zhou

Video grounding aims to localize the corresponding video moment in an untrimmed video given a language query. Existing methods often address this task in an indirect way, by casting it as a proposal-and-match or fusion-and-detection…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Fengyuan Shi , Weilin Huang , Limin Wang

In this work, we propose a novel paradigm to encode the position of targets for target tracking in videos using transformers. The proposed paradigm, Dense Spatio-Temporal (DST) position encoding, encodes spatio-temporal position information…

Computer Vision and Pattern Recognition · Computer Science 2022-10-19 Jinkun Cao , Hao Wu , Kris Kitani

Recently, various studies have been directed towards exploring dense passage retrieval techniques employing pre-trained language models, among which the masked auto-encoder (MAE) pre-training architecture has emerged as the most promising.…

Information Retrieval · Computer Science 2023-05-23 Zehan Li , Yanzhao Zhang , Dingkun Long , Pengjun Xie

Image captioning generates text that describes scenes from input images. It has been developed for high quality images taken in clear weather. However, in bad weather conditions, such as heavy rain, snow, and dense fog, the poor visibility…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Chang-Hwan Son , Pung-Hwi Ye

Video captioning aims to automatically generate natural language sentences that can describe the visual contents of a given video. Existing generative models like encoder-decoder frameworks cannot explicitly explore the object-level…

Computer Vision and Pattern Recognition · Computer Science 2021-08-11 Yang Bai , Junyan Wang , Yang Long , Bingzhang Hu , Yang Song , Maurice Pagnucco , Yu Guan