Related papers: Sculpting the Vector Space: Towards Efficient Mult…

Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and memory overhead during inference. To address this issue, we…

This paper presents a novel approach to neural network compression that addresses redundancy at both the filter and architectural levels through a unified framework grounded in information flow analysis. Building on the concept of tensor…

Recently, vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks. Yet the high computational costs and training data requirements of ViTs limit their application in…

Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document…

Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR…

Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typically consider only the textual content within documents,…

While Large Vision Language Models (LVLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose deployment challenges on resource-constrained edge devices. Current parameter reduction techniques…

Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into…

Transformer architecture has gained popularity due to its ability to scale with large dataset. Consequently, there is a need to reduce the model size and latency, especially for on-device deployment. We focus on vision transformer proposed…

Composed image retrieval (CIR) aims to retrieve the target image based on a multimodal query, i.e., a reference image paired with corresponding modification text. Recent CIR studies leverage vision-language pre-trained (VLP) methods as the…

Video-Text Retrieval (VTR) aims to search for the most relevant video related to the semantics in a given sentence, and vice versa. In general, this retrieval task is composed of four successive steps: video and textual feature…

In a retrieval system, simultaneously achieving search accuracy and efficiency is inherently challenging. This challenge is particularly pronounced in partially relevant video retrieval (PRVR), where incorporating more diverse context…

In recent years, numerous real-time stereo matching methods have been introduced, but they often lack accuracy. These methods attempt to improve accuracy by introducing new modules or integrating traditional methods. However, the…

Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retrieval. We introduce a model that is able to represent the…

This is a further development of Vision Transformer Pruning via matrix decomposition. The purpose of the Vision Transformer Pruning is to prune the dimension of the linear projection of the dataset by learning their associated importance…

Given a video and a linguistic query, video moment retrieval and highlight detection (MR&HD) aim to locate all the relevant spans while simultaneously predicting saliency scores. Most existing methods utilize RGB images as input,…

Traditional information retrieval is based on sparse bag-of-words vector representations of documents and queries. More recent deep-learning approaches have used dense embeddings learned using a transformer-based large language model. We…

In autonomous driving, robust place recognition is critical for global localization and loop closure detection. While inter-modality fusion of camera and LiDAR data in multimodal place recognition (MPR) has shown promise in overcoming the…

Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information. Yet, they face significant challenges due to the high computational and memory demands of processing long sequences…

Compared with still image object detection, video object detection (VOD) needs to particularly concern the high across-frame variation in object appearance, and the diverse deterioration in some frames. In principle, the detection in a…