中文
相关论文

相关论文: DIBS: Enhancing Dense Video Captioning with Unlabe…

200 篇论文

Dense image captioning is critical for cross-modal alignment in vision-language pretraining and text-to-image generation, but scaling expert-quality annotations is prohibitively expensive. While synthetic captioning via strong…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Tzu-Heng Huang , Sirajul Salekin , Javier Movellan , Frederic Sala , Manjot Bilkhu

Image captioning models are usually trained according to human annotated ground-truth captions, which could generate accurate but generic captions. In this paper, we focus on generating distinctive captions that can distinguish the target…

计算机视觉与模式识别 · 计算机科学 2022-08-30 Youyuan Zhang , Jiuniu Wang , Hao Wu , Wenjia Xu

Recent advancements in multimodal models highlight the value of rewritten captions for improving performance, yet key challenges remain. For example, while synthetic captions often provide superior quality and image-text alignment, it is…

计算机视觉与模式识别 · 计算机科学 2024-10-04 Zhengfeng Lai , Vasileios Saveris , Chen Chen , Hong-You Chen , Haotian Zhang , Bowen Zhang , Juan Lao Tebar , Wenze Hu , Zhe Gan , Peter Grasch , Meng Cao , Yinfei Yang

Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs…

机器学习 · 计算机科学 2024-06-18 Jiahan Zhang , Qi Wei , Feng Liu , Lei Feng

Video-text retrieval has been stuck in the information mismatch caused by personalized and inadequate textual descriptions of videos. The substantial information gap between the two modalities hinders an effective cross-modal representation…

计算机视觉与模式识别 · 计算机科学 2025-04-09 Baoyao Yang , Junxiang Chen , Wanyun Li , Wenbin Yao , Yang Zhou

With the advancement of large pre-trained vision-language models, effectively transferring the knowledge embedded within these foundational models to downstream tasks has become a pivotal topic, particularly in data-scarce environments.…

计算机视觉与模式识别 · 计算机科学 2024-09-12 Tianxiang Hao , Mengyao Lyu , Hui Chen , Sicheng Zhao , Xiaohan Ding , Jungong Han , Guiguang Ding

Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods on dense video captioning tackle this problem by building…

计算机视觉与模式识别 · 计算机科学 2018-04-04 Luowei Zhou , Yingbo Zhou , Jason J. Corso , Richard Socher , Caiming Xiong

Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow generation speed and large cumulative error. Furthermore,…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Junbo Wang , Liangyu Fu , Yuke Li , Yining Zhu , Ya Jing , Xuecheng Wu , Jiangbin Zheng

In this paper, we address a fundamental gap between pre-training and fine-tuning of deep neural networks: while pre-training has shifted from unimodal to multimodal learning with enhanced visual understanding, fine-tuning predominantly…

计算机视觉与模式识别 · 计算机科学 2026-01-30 Shohei Enomoto , Shin'ya Yamaguchi

Self-supervised learning algorithms, including BERT and SimCLR, have enabled significant strides in fields like natural language processing, computer vision, and speech processing. However, these algorithms are domain-specific, meaning that…

机器学习 · 计算机科学 2023-01-09 Alex Tamkin , Vincent Liu , Rongfei Lu , Daniel Fein , Colin Schultz , Noah Goodman

The Audio-Visual Video Parsing task aims to identify and temporally localize the events that occur in either or both the audio and visual streams of audible videos. It often performs in a weakly-supervised manner, where only video event…

计算机视觉与模式识别 · 计算机科学 2024-06-04 Jinxing Zhou , Dan Guo , Yiran Zhong , Meng Wang

Foundation models have achieved remarkable results in 2D and language tasks like image segmentation, object detection, and visual-language understanding. However, their potential to enrich 3D scene representation learning is largely…

计算机视觉与模式识别 · 计算机科学 2023-11-03 Zhimin Chen , Longlong Jing , Yingwei Li , Bing Li

Vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated impressive results in natural image domains. However, these models often struggle when applied to specialized domains like remote sensing, and…

计算机视觉与模式识别 · 计算机科学 2023-10-26 Sangwoo Mo , Minkyu Kim , Kyungmin Lee , Jinwoo Shin

We introduce NimbleD, an efficient self-supervised monocular depth estimation learning framework that incorporates supervision from pseudo-labels generated by a large vision model. This framework does not require camera intrinsics, enabling…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Albert Luginov , Muhammad Shahzad

Weakly-Supervised Dense Video Captioning aims to localize and describe events in videos trained only on caption annotations, without temporal boundaries. Prior work introduced an implicit supervision paradigm based on Gaussian masking and…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Ye-Chan Kim , SeungJu Cha , Si-Woo Kim , Minju Jeon , Hyungee Kim , Dong-Jin Kim

Dense video captioning aims to generate corresponding text descriptions for a series of events in the untrimmed video, which can be divided into two sub-tasks, event detection and event captioning. Unlike previous works that tackle the two…

计算机视觉与模式识别 · 计算机科学 2023-07-24 Qi Zhang , Yuqing Song , Qin Jin

We propose a novel end-to-end curriculum learning approach for sparsely labelled animal datasets leveraging large volumes of unlabelled data to improve supervised species detectors. We exemplify the method in detail on the task of finding…

计算机视觉与模式识别 · 计算机科学 2023-01-03 Xinyu Yang , Tilo Burghardt , Majid Mirmehdi

Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…

计算机视觉与模式识别 · 计算机科学 2024-07-09 Haonan Xu , Dian Chao , Xiangyu Wu , Zhonghua Wan , Yang Yang

The recent advance in vision-language models is largely attributed to the abundance of image-text data. We aim to replicate this success for video-language models, but there simply is not enough human-curated video-text data available. We…

计算机视觉与模式识别 · 计算机科学 2024-04-17 Yue Zhao , Long Zhao , Xingyi Zhou , Jialin Wu , Chun-Te Chu , Hui Miao , Florian Schroff , Hartwig Adam , Ting Liu , Boqing Gong , Philipp Krähenbühl , Liangzhe Yuan

Recently, sign language researchers have turned to sign language interpreted TV broadcasts, comprising (i) a video of continuous signing and (ii) subtitles corresponding to the audio content, as a readily available and large-scale source of…

计算机视觉与模式识别 · 计算机科学 2022-08-05 Liliane Momeni , Hannah Bull , K R Prajwal , Samuel Albanie , Gül Varol , Andrew Zisserman