Related papers: DARC-CLIP: Dynamic Adaptive Refinement with Cross-…

Social networks can be a valuable source of information during crisis events. In particular, users can post a stream of multimodal data that can be critical for real-time humanitarian response. However, effectively extracting meaningful…

Detecting transitions between intro/credits and main content in videos is a crucial task for content segmentation, indexing, and recommendation systems. Manual annotation of such transitions is labor-intensive and error-prone, while…

This study investigates the cognitive plausibility of a pretrained multimodal model, CLIP, in recognizing emotions evoked by abstract visual art. We employ a dataset comprising images with associated emotion labels and textual rationales of…

Cultural context profoundly shapes how people interpret online content, yet vision-language models (VLMs) remain predominantly trained through Western or English-centric lenses. This limits their fairness and cross-cultural robustness in…

The rapid rise of video content on platforms such as TikTok and YouTube has transformed information dissemination, but it has also facilitated the spread of harmful content, particularly hate videos. Despite significant efforts to combat…

The interplay between the image and comment on a social media post is one of high importance for understanding its overall message. Recent strides in multimodal embedding models, namely CLIP, have provided an avenue forward in relating…

Masked Image Modeling (MIM) methods, like Masked Autoencoders (MAE), efficiently learn a rich representation of the input. However, for adapting to downstream tasks, they require a sufficient amount of labeled data since their rich features…

The rise in the number of social media users has led to an increase in the hateful content posted online. In countries like India, where multiple languages are spoken, these abhorrent posts are from an unusual blend of code-switched…

Multimodal fusion breaks through the boundaries between diverse modalities and has already achieved notable performances. However, in many specialized fields, it is struggling to obtain sufficient alignment data for training, which…

Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various architectures, from vision transformers (ViTs) to convolutional networks (ResNets) have been trained with CLIP to…

The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box…

Hateful videos present serious risks to online safety and real-world well-being, necessitating effective detection methods. Although multimodal classification approaches integrating information from several modalities outperform unimodal…

The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP…

Medical anomaly detection (MAD) and segmentation play a critical role in assisting clinical diagnosis by identifying abnormal regions in medical images and localizing pathological regions. Recent CLIP-based studies are promising for anomaly…

Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e.g. achieving 76.3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits…

While vision-language models like CLIP have shown remarkable success in open-vocabulary tasks, their application is currently confined to image-level tasks, and they still struggle with dense predictions. Recent works often attribute such…

Contrastive Language-Image Pre-training (CLIP) is an approach that has advanced research and applications in computer vision, fueling modern recognition systems and generative models. We believe that the main ingredient to the success of…

Understanding human intentions (e.g., emotions) from videos has received considerable attention recently. Video streams generally constitute a blend of temporal data stemming from distinct modalities, including natural language, facial…

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictions. Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced to…

We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone utilizes visual prompt…