English
Related papers

Related papers: Synergy-CLIP: Extending CLIP with Multi-modal Inte…

200 papers

Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Md Zarif Hossain , Ahmed Imteaj

Multimodal representation learning aims to construct a shared embedding space in which heterogeneous modalities are semantically aligned. Despite strong empirical results, InfoNCE-based objectives introduce inherent conflicts that yield…

Machine Learning · Computer Science 2026-02-11 Wenzhe Yin , Pan Zhou , Zehao Xiao , Jie Liu , Shujian Yu , Jan-Jakob Sonke , Efstratios Gavves

Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Austin Stone , Hagen Soltau , Robert Geirhos , Xi Yi , Ye Xia , Bingyi Cao , Kaifeng Chen , Abhijit Ogale , Jonathon Shlens

Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Yufeng Cui , Lichen Zhao , Feng Liang , Yangguang Li , Jing Shao

Recent advancements in image-text matching have been notable, yet prevailing models predominantly cater to broad queries and struggle with accommodating fine-grained query intention. In this paper, we work towards the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Yaxiong Wang , Yujiao Wu , Lianwei Wu , Lechao Cheng , Zhun Zhong , Meng Wang

Multi-modal semantic understanding requires integrating information from different modalities to extract users' real intention behind words. Most previous work applies a dual-encoder structure to separately encode image and text, but fails…

Computation and Language · Computer Science 2024-03-12 Ming Zhang , Ke Chang , Yunfang Wu

Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text modalities. Despite its widespread adoption, a significant…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Beichen Zhang , Pan Zhang , Xiaoyi Dong , Yuhang Zang , Jiaqi Wang

Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Zhichao Yang , Leida Li , Pengfei Chen , Jinjian Wu , Giuseppe Valenzise

The application of Contrastive Language-Image Pre-training (CLIP) in Weakly Supervised Semantic Segmentation (WSSS) research powerful cross-modal semantic understanding capabilities. Existing methods attempt to optimize input text prompts…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Zhongxing Xu , Feilong Tang , Zhe Chen , Yingxue Su , Zhiyi Zhao , Ge Zhang , Jionglong Su , Zongyuan Ge

Referring Image Segmentation (RIS) is a cross-modal task that aims to segment an instance described by a natural language expression. Recent methods leverage large-scale pretrained unimodal models as backbones along with fusion techniques…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Seoyeon Kim , Minguk Kang , Dongwon Kim , Jaesik Park , Suha Kwak

The Contrastive Language-Image Pre-training (CLIP) Model is a recently proposed large-scale pre-train model which attracts increasing attention in the computer vision community. Benefiting from its gigantic image-text training set, the CLIP…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Yuxuan Ding , Lingqiao Liu , Chunna Tian , Jingyuan Yang , Haoxuan Ding

We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Aman Shrivastava , Ramprasaath R. Selvaraju , Nikhil Naik , Vicente Ordonez

We propose a novel framework for ID-preserving generation using a multi-modal encoding strategy rather than injecting identity features via adapters into pre-trained models. Our method treats identity and text as a unified conditioning…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Zichuan Liu , Liming Jiang , Qing Yan , Yumin Jia , Hao Kang , Xin Lu

Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in multimodal intelligence. However, recent studies discovered that CLIP can only encode one aspect of the feature space, leading to substantial information loss and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Jihai Zhang , Xiaoye Qu , Tong Zhu , Yu Cheng

In this paper, we demonstrate that CLIP can also be adapted to downstream tasks where its vision-language alignment is suboptimally learned during pre-training on web-crawled data, all without requiring fine-tuning. We explore the case of…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Sohee Kim , Jisu Kang , Dunam Kim , Seokju Lee

Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Giordano Cicchetti , Eleonora Grassucci , Luigi Sigillo , Danilo Comminiello

Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Kaicheng Yang , Jiankang Deng , Xiang An , Jiawei Li , Ziyong Feng , Jia Guo , Jing Yang , Tongliang Liu

While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems remains a challenge, due to issues like training objective…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Josh Beal , Eric Kim , Jinfeng Rao , Rex Wu , Dmitry Kislyuk , Charles Rosenberg

The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Tuo Xiang , Xuemiao Xu , Bangzhen Liu , Jinyi Li , Yong Li , Shengfeng He

Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse downstream tasks. However, several pain points persist for this paradigm: (i) directly tuning entire pre-trained models becomes both time-intensive…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Chenyu You , Yifei Min , Weicheng Dai , Jasjeet S. Sekhon , Lawrence Staib , James S. Duncan