Search Results for « CLIP-based models »

Text-based Person Search (TBPS) aims to retrieve the person images using natural language descriptions. Recently, Contrastive Language Image Pretraining (CLIP), a universal large cross-modal vision-language pre-training model, has remarkably performed over various cross-modal downstream tasks due to its powerful cross-modal semantic learning capacity. TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS. In order to explore the potential of the visual-language pre-training model for downstream TBPS tasks, this paper makes the first attempt to conduct a comprehensive empirical study of CLIP for TBPS and thus contribute a straightforward, incremental, yet strong TBPS-CLIP baseline to the TBPS community. We revisit critical design considerations under CLIP, including data augmentation and loss function. The model, with the aforementioned designs and practical training tricks, can attain satisfactory performance without any sophisticated modules. Also, we conduct the probing experiments of TBPS-CLIP in model generalization and model compression, demonstrating the effectiveness of TBPS-CLIP from various aspects. This work is expected to provide empirical insights and highlight future CLIP-based TBPS research.

Human motion generation is essential for fields such as animation, robotics, and virtual reality, requiring models that effectively capture motion dynamics from text descriptions. Existing approaches often rely on Contrastive Language-Image Pretraining (CLIP)-based text encoders, but their training on text-image pairs constrains their ability to understand temporal and kinematic structures inherent in motion and motion generation. This work introduces MoCLIP, a fine-tuned CLIP model with an additional motion encoding head, trained on motion sequences using contrastive learning and tethering loss. By explicitly incorporating motion-aware representations, MoCLIP enhances motion fidelity while remaining compatible with existing CLIP-based pipelines and seamlessly integrating into various CLIP-based methods. Experiments demonstrate that MoCLIP improves Top-1, Top-2, and Top-3 accuracy while maintaining competitive FID, leading to improved text-to-motion alignment results. These results highlight MoCLIP's versatility and effectiveness, establishing it as a robust framework for enhancing motion generation.

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a Gradient-based visual and textual Explanation method for CLIP (Grad-ECLIP), which interprets the matching result of CLIP for specific input image-text pair. By decomposing the architecture of the encoder and discovering the relationship between the matching similarity and intermediate spatial features, Grad-ECLIP produces effective heat maps that show the influence of image regions or words on the CLIP results. Different from the previous Transformer interpretation methods that focus on the utilization of self-attention maps, which are typically extremely sparse in CLIP, we produce high-quality visual explanations by applying channel and spatial weights on token features. Qualitative and quantitative evaluations verify the effectiveness and superiority of Grad-ECLIP compared with the state-of-the-art methods. Furthermore, a series of analysis are conducted based on our visual and textual explanation results, from which we explore the working mechanism of image-text matching, the strengths and limitations in attribution identification of CLIP, and the relationship between the concreteness/abstractness of a word and its usage in CLIP. Finally, based on the ability of explanation map that indicates text-specific saliency region of input image, we also propose an application with Grad-ECLIP, which is adopted to boost the fine-grained alignment in the CLIP fine-tuning. The code of Grad-ECLIP is available here: https://github.com/Cyang-Zhao/Grad-Eclip.

Abstract In this study, we present a comprehensive evaluation of Contrastive Language-Image Pre-training (CLIP) for zero-shot electrocardiogram (ECG) classification across multiple datasets and diagnostic classes. Traditional ECG classification models require significant labeled training data for every diagnostic class, limiting their adaptability to new or unseen classes. To address this limitation, we trained and evaluated 24 CLIP-based models, composed of one image encoder (CNN Base, CNN V2, CNN V3, RNN, ISIBrno) and one text encoder (BioBERT, Bio+ClinicalBERT, bert-case-uncased) on 27 seen classes on three datasets (PTB-XL, Ningbo, and Gerogia) and evaluated zero-shot classification performance on 11 unseen classes. We investigate the impact of training dataset size, encoder architectures, and pretraining effects on both in-distribution and out-of-distribution generalization performance. Our experiments included internal evaluation (Experiment A) and external validation on two independent datasets (SPH and CODE-15%, Experiment B). The top-performing models achieves a macro-averaged ROC-AUC of 0.70 for zero-shot out-of-distribution classification, 0.70 for zero-shot in-distribution classification, and 0.83 for out-of-distribution classification with classic training. These results demonstrate that CLIP-based models can meaningfully classify ECG conditions beyond the scope of their training, offering a flexible alternative to current ECG diagnostic systems where clinical needs are constantly evolving.

Earth observation (EO) spans a broad spectrum of modalities, including optical, radar, multispectral, and hyperspectral data, each capturing distinct environmental signals. However, current vision-language models in EO, particularly CLIP-based variants, remain confined to individual modalities, limiting generalization and scalability across diverse tasks. We present DOFA-CLIP (Dynamic-One-For-All CLIP), a unified vision-language foundation model that dynamically adapts to EO modalities with flexible spectral configurations through a single Transformer backbone. Our approach introduces three key contributions: 1) the construction of GeoLangBind-2M, a large-scale EO image-text dataset covering six heterogeneous modalities with rich natural language descriptions; 2) a novel training strategy called VECT (Vision-models Enhanced Contrastive Text-image pretraining), which enhances the spatial awareness of CLIP features with multiple vision foundation models; and 3) a Modality-aware Knowledge Agglomeration (MaKA) module that refines feature distillation with modality-specific awareness. DOFA-CLIP achieves state-of-the-art zero-shot performance across a wide range of EO benchmarks, including unseen modalities and a diverse number of input spectral bands. Together, these contributions establish a scalable foundation for multimodal EO understanding and open new avenues for integrating heterogeneous EO data with large language models. Code and datasets will be released. Code and datasets are publicly available.

Text-to-image synthesis, a subfield of multimodal generation, has gained significant attention in recent years. We propose a cost-effective approach for image-to-prompt generation that leverages generative models to generate textual prompts without the need for large amounts of annotated data. We divide our method into two stages: online stage and offline stage. We use a combination of the CLIP model and K-nearest neighbors (KNN) algorithm. The proposed system consists of two main parts: an offline task and an online task. Our method owns the highest metric 0.612 among these models, which is 0.013, 0.055, 0.011 higher than Clip, Clip + KNN(top 10) respectively.