中文
相关论文

相关论文: BiMa: Towards Biases Mitigation for Text-Video Ret…

200 篇论文

Many studies focus on improving pretraining or developing new backbones in text-video retrieval. However, existing methods may suffer from the learning and inference bias issue, as recent research suggests in other text-video-related tasks.…

计算机视觉与模式识别 · 计算机科学 2023-09-19 Burak Satar , Hongyuan Zhu , Hanwang Zhang , Joo Hwee Lim

As online video content rapidly grows, the task of text-video retrieval (TVR) becomes increasingly important. A key challenge in TVR is the information asymmetry between video and text: videos are inherently richer in information, while…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Zechen Bai , Tianjun Xiao , Tong He , Pichao Wang , Zheng Zhang , Thomas Brox , Mike Zheng Shou

Video Moment Retrieval (VMR) aims to retrieve relevant moments of an untrimmed video corresponding to the query. While cross-modal interaction approaches have shown progress in filtering out query-irrelevant information in videos, they…

人工智能 · 计算机科学 2024-08-26 Chenghua Gao , Min Li , Jianshuo Liu , Junxing Ren , Lin Chen , Haoyu Liu , Bo Meng , Jitao Fu , Wenwen Su

Text-to-video retrieval (TVR) aims to find the most relevant video in a large video gallery given a query text. The intricate and abundant context of the video challenges the performance and efficiency of TVR. To handle the serialized video…

计算机视觉与模式识别 · 计算机科学 2023-11-02 Mengxia Wu , Min Cao , Yang Bai , Ziyin Zeng , Chen Chen , Liqiang Nie , Min Zhang

Pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable performance across various downstream tasks by aligning text and images in a unified embedding space. However, due to the imbalanced distribution of…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Yunfan Yang , Chaoquan Jiang , Zhiyu Lin , Jinlin Xiao , Jiaming Zhang , Jitao Sang

Recently, Large Vision-Language Models (LVLMs) have made significant strides across diverse multimodal tasks and benchmarks. This paper reveals a largely under-explored problem from existing video-involved LVLMs - language bias, where…

计算机视觉与模式识别 · 计算机科学 2025-02-25 Yiming Yang , Yangyang Guo , Hui Lu , Yan Wang

Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being…

计算机视觉与模式识别 · 计算机科学 2024-11-08 Walter Gerych , Haoran Zhang , Kimia Hamidieh , Eileen Pan , Maanas Sharma , Thomas Hartvigsen , Marzyeh Ghassemi

Large pre-trained vision-language models (VLMs) reduce the time for developing predictive models for various vision-grounded language downstream tasks by providing rich, adaptable image and text representations. However, these models suffer…

计算机视觉与模式识别 · 计算机科学 2023-03-21 Ashish Seth , Mayur Hemani , Chirag Agarwal

Addressing biases in computer vision models is crucial for real-world AI deployments. However, mitigating visual biases is challenging due to their unexplainable nature, often identified indirectly through visualization or sample…

机器学习 · 计算机科学 2024-03-28 Younghyun Kim , Sangwoo Mo , Minkyu Kim , Kyungmin Lee , Jaeho Lee , Jinwoo Shin

Temporal sentence grounding (TSG) is an important yet challenging task in multimedia information retrieval. Although previous TSG methods have achieved decent performance, they tend to capture the selection biases of frequently appeared…

计算机视觉与模式识别 · 计算机科学 2022-07-28 Daizong Liu , Xiaoye Qu , Wei Hu

Mitigating biases in computer vision models is an essential step towards the trustworthiness of artificial intelligence models. Existing bias mitigation methods focus on a small set of predefined biases, limiting their applicability in…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Ioannis Sarridis , Christos Koutlis , Symeon Papadopoulos , Christos Diou

Vision-language models (VLMs) have demonstrated impressive performance by effectively integrating visual and textual information to solve complex tasks. However, it is not clear how these models reason over the visual and textual data…

人工智能 · 计算机科学 2025-04-15 Pouya Pezeshkpour , Moin Aminnaseri , Estevam Hruschka

Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. The complexity of this task increases with the intricacy of the sentences provided. Existing…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Hai Nguyen-Truong , E-Ro Nguyen , Tuan-Anh Vu , Minh-Triet Tran , Binh-Son Hua , Sai-Kit Yeung

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we…

Video-Text Retrieval (VTR) aims to search for the most relevant video related to the semantics in a given sentence, and vice versa. In general, this retrieval task is composed of four successive steps: video and textual feature…

计算机视觉与模式识别 · 计算机科学 2023-02-27 Cunjuan Zhu , Qi Jia , Wei Chen , Yanming Guo , Yu Liu

Video moment retrieval (VMR) aims to localize target moments in untrimmed videos pertinent to a given textual query. Existing retrieval systems tend to rely on retrieval bias as a shortcut and thus, fail to sufficiently learn multi-modal…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Sunjae Yoon , Ji Woo Hong , Eunseop Yoon , Dahyun Kim , Junyeong Kim , Hee Suk Yoon , Chang D. Yoo

In recent years, recognition of text from natural scene image and video frame has got increased attention among the researchers due to its various complexities and challenges. Because of low resolution, blurring effect, complex background,…

计算机视觉与模式识别 · 计算机科学 2017-07-31 Ayan Kumar Bhunia , Gautam Kumar , Partha Pratim Roy , R. Balasubramanian , Umapada Pal

We propose a new "Unbiased through Textual Description (UTD)" video benchmark based on unbiased subsets of existing video classification and retrieval datasets to enable a more robust assessment of video understanding capabilities. Namely,…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Nina Shvetsova , Arsha Nagrani , Bernt Schiele , Hilde Kuehne , Christian Rupprecht

Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Haozhe Zhao , Shuzheng Si , Liang Chen , Yichi Zhang , Maosong Sun , Mingjia Zhang , Baobao Chang

Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…

计算机视觉与模式识别 · 计算机科学 2026-05-28 Seung Hyuk Lee , Songkuk Kim
‹ 上一页 1 2 3 10 下一页 ›