Related papers: Delving into E-Commerce Product Retrieval with Vis…
We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pretraining (MAC), for video-text retrieval tasks. Our MAC aims to reduce video representation's spatial and…
Retrieval augmentation, which enhances downstream models by a knowledge retriever and an external corpus instead of by merely increasing the number of model parameters, has been successfully applied to many natural language processing (NLP)…
On large-scale e-commerce platforms with tens of millions of active monthly users, recommending visually similar products is essential for enabling users to efficiently discover items that align with their preferences. This study presents…
Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business…
Large-scale e-commerce search must surface a broad set of items from a vast catalog, ranging from bestselling products to new, trending, or seasonal items. Modern systems therefore rely on multiple specialized retrieval channels to surface…
Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as bags of concepts, underrepresenting structured visual relationships such as pose and viewpoint. We proposeVisualize-then-Retrieve…
Recent large-scale video-language pre-trained models have shown appealing performance on various downstream tasks. However, the pre-training process is computationally expensive due to the requirement of millions of video-text pairs and the…
Generative retrieval introduces a groundbreaking paradigm to document retrieval by directly generating the identifier of a pertinent document in response to a specific query. This paradigm has demonstrated considerable benefits and…
In this paper, we present a unified end-to-end approach to build a large scale Visual Search and Recommendation system for e-commerce. Previous works have targeted these problems in isolation. We believe a more effective and elegant…
We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that…
We present CLIP2Video network to transfer the image-language pre-training model to video-text retrieval in an end-to-end manner. Leading approaches in the domain of video-and-language learning try to distill the spatio-temporal video…
Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video…
Real-world vision-language applications demand varying levels of perceptual granularity. However, most existing visual large language models (VLLMs), such as LLaVA, pre-assume a fixed resolution for downstream tasks, which leads to subpar…
Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise similarity computation in contrastive loss between image and…
Vision-language (VL) Pre-training (VLP) has shown to well generalize VL models over a wide range of VL downstream tasks, especially for cross-modal retrieval. However, it hinges on a huge amount of image-text pairs, which requires tedious…
Recently, Vision-Language Pre-training (VLP) techniques have greatly benefited various vision-language tasks by jointly learning visual and textual representations, which intuitively helps in Optical Character Recognition (OCR) tasks due to…
Recent work in vision-and-language demonstrates that large-scale pretraining can learn generalizable models that are efficiently transferable to downstream tasks. While this may improve dataset-scale aggregate metrics, analyzing performance…
Transformers have shown outstanding results for natural language understanding and, more recently, for image classification. We here extend this work and propose a transformer-based approach for image retrieval: we adopt vision transformers…
Recent advancements in Large Vision-Language Models have showcased remarkable capabilities. However, they often falter when confronted with complex reasoning tasks that humans typically address through visual aids and deliberate,…
Recent high-capacity vision-language-action (VLA) models have demonstrated impressive performance on a range of robotic manipulation tasks by imitating human demonstrations. However, exploiting offline data with limited visited states will…