Related papers: Visual Zero-Shot E-Commerce Product Attribute Valu…

Image recognition has recently witnessed a paradigm shift, where vision-language models are now used to perform few-shot classification based on textual prompts. Among these, the CLIP model has shown remarkable capabilities for zero-shot…

Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot generate-and-encode pipeline: a vision-language model first…

Attribute Value Extraction (AVE) is important for structuring product information in e-commerce. However, existing AVE datasets are primarily limited to text-to-text or image-to-text settings, lacking support for product videos, diverse…

E-commerce product understanding demands by nature, strong multimodal comprehension from text, images, and structured attributes. General-purpose Vision-Language Models (VLMs) enable generalizable multimodal latent modelling, yet there is…

Addressing multi-label action recognition in videos represents a significant challenge for robotic applications in dynamic environments, especially when the robot is required to cooperate with humans in tasks that involve objects. Existing…

Pre-trained Vision-Language Models (VLMs) struggle with Zero-Shot Anomaly Detection (ZSAD) due to a critical adaptation gap: they lack the local inductive biases required for dense prediction and employ inflexible feature fusion paradigms.…

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…

Current Large Vision Language Models (LVLMs) excel at many zero-shot tasks like image captioning, visual question answering and OCR. However, these same models suffer from poor performance at image classification tasks, underperforming…

X-ray prohibited item detection is an essential component of security check and categories of prohibited item are continuously increasing in accordance with the latest laws. Previous works all focus on close-set scenarios, which can only…

Contrastive vision-language models, such as CLIP, have garnered considerable attention for various downstream tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often…

CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks. We demonstrate that CLIP is vulnerable to change in image quality under compression. This surprising…

In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training. We focus on the transductive setting, in which unlabelled visual data from unseen…

Measuring the perception of visual content is a long-standing problem in computer vision. Many mathematical models have been developed to evaluate the look or quality of an image. Despite the effectiveness of such tools in quantifying…

Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmentation. Adapting these models for object counting, however,…

The goal of spatial-temporal action detection is to determine the time and place where each person's action occurs in a video and classify the corresponding action category. Most of the existing methods adopt fully-supervised learning,…

When fine-tuning zero-shot models like CLIP, our desideratum is for the fine-tuned model to excel in both in-distribution (ID) and out-of-distribution (OOD). Recently, ensemble-based models (ESM) have been shown to offer significant…

Domain adaptation is crucial in aerial imagery, as the visual representation of these images can significantly vary based on factors such as geographic location, time, and weather conditions. Additionally, high-resolution aerial images…

Semantic segmentation has a broad range of applications, but its real-world impact has been significantly limited by the prohibitive annotation costs necessary to enable deployment. Segmentation methods that forgo supervision can side-step…

Existing multi-object tracking algorithms typically fail to adequately address the issues in low-quality videos, resulting in a significant decline in tracking performance when image quality deteriorates in real-world scenarios. This…

Visual defect detection is critical to ensure the quality of most products. However, the majority of small and medium-sized manufacturing enterprises still rely on tedious and error-prone human manual inspection. The main reasons include:…