相关论文: Beat: Bi-directional One-to-Many Embedding Alignme…

With the explosive growth of web videos and emerging large-scale vision-language pre-training models, e.g., CLIP, retrieving videos of interest with text instructions has attracted increasing attention. A common practice is to transfer…

Recent information retrieval (IR) models are pre-trained and instruction-tuned on massive datasets and tasks, enabling them to perform well on a wide range of tasks and potentially generalize to unseen tasks with instructions. However,…

We introduce a model for bidirectional retrieval of images and sentences through a multi-modal embedding of visual and natural language data. Unlike previous models that directly map images or sentences into a common embedding space, our…

Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or…

Most existing person re-identification (re-id) models focus on matching still person images across disjoint camera views. Since only limited information can be exploited from still images, it is hard (if not impossible) to overcome the…

Text-based Pedestrian Retrieval (TPR) deals with retrieving specific target pedestrians in visual scenes according to natural language descriptions. Although existing methods have achieved progress under constrained settings, interactive…

In this work, we focus on text-based person retrieval, which identifies individuals based on textual descriptions. Despite advancements enabled by synthetic data for pretraining, a significant domain gap, due to variations in lighting,…

Most existing person re-identification (ReID) methods rely only on the spatial appearance information from either one or multiple person images, whilst ignore the space-time cues readily available in video or image-sequence data. Moreover,…

LLMs confront inherent limitations in terms of its knowledge, memory, and action. The retrieval augmentation stands as a vital mechanism to address these limitations, which brings in useful information from external sources to augment the…

Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be…

In this paper, we investigate a new approach to Population, Intervention and Outcome (PIO) element detection, a common task in Evidence Based Medicine (EBM). The purpose of this study is two-fold: to build a training dataset for PIO element…

Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the…

Text embedding models play a cornerstone role in AI applications, such as retrieval-augmented generation (RAG). While general-purpose text embedding models demonstrate strong performance on generic retrieval benchmarks, their effectiveness…

Multi-person human mesh recovery from a single image is a challenging task, hindered by the scarcity of in-the-wild training data. Prevailing in-the-wild human mesh pseudo-ground-truth (pGT) generation pipelines are single-person-centric,…

Retrieval-Augmented Generation (RAG) has emerged as a promising technique to enhance the quality and relevance of responses generated by large language models. While recent advancements have mainly focused on improving RAG for text-based…

Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve…

GRAP-MOT is a new approach for solving the person MOT problem dedicated to videos of closed areas with overlapping multi-camera views, where person occlusion frequently occurs. Our novel graph-weighted solution updates a person's…

Multi-object tracking (MOT) is a fundamental problem in computer vision with numerous applications, such as intelligent surveillance and automated driving. Despite the significant progress made in MOT, pedestrian attributes, such as gender,…

Text-based person search, employing free-form text queries to identify individuals within a vast image collection, presents a unique challenge in aligning visual and textual representations, particularly at the human part level. Existing…

We simplify space binding by focusing on two core components, a single encoder per modality and high-quality data; enabling training state-of-the-art models on a single GPU in a few hours as opposed to multiple days. We present EBind, an…