Related papers: Sculpting the Vector Space: Towards Efficient Mult…
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…
DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for…
Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art methods employ Vision Transformers (ViTs) as backbone foundation models to extract…
Since its inception, Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. Nonetheless, the multi-head self-attention (MHSA) mechanism in ViT is computationally expensive due to its calculation of…
Although Multimodal Large Language Models (MLLMs) have shown remarkable potential in Visual Document Retrieval (VDR) through generating high-quality multi-vector embeddings, the substantial storage overhead caused by representing a page…
Businesses need to query visually rich documents (VRDs) like receipts, medical records, and insurance forms to make decisions. Existing techniques for extracting entities from VRDs struggle with new layouts or require extensive pre-training…
Embedding models can generate high-dimensional vectors whose similarity reflects semantic affinities. Thus, accurately and timely retrieving those vectors in a large collection that are similar to a given query has become a critical…
As we push the boundaries of performance in various vision tasks, the models grow in size correspondingly. To keep up with this growth, we need very aggressive pruning techniques for efficient inference and deployment on edge devices.…
In content-based video retrieval (CBVR), dealing with large-scale collections, efficiency is as important as accuracy; thus, several video-level feature-based studies have actively been conducted. Nevertheless, owing to the severe…
Vision Transformer (ViT) has achieved impressive results across various vision tasks, yet its high computational cost limits practical applications. Recent methods have aimed to reduce ViT's $O(n^2)$ complexity by pruning unimportant…
Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression ratios cannot adapt to scenes of varying complexity, often…
Current structural pruning methods face two significant limitations: (i) they often limit pruning to finer-grained levels like channels, making aggressive parameter reduction challenging, and (ii) they focus heavily on parameter and FLOP…
The rapid growth of video content demands efficient and precise retrieval systems. While vision-language models (VLMs) excel in representation learning, they often struggle with adaptive, time-sensitive video retrieval. This paper…
Text-to-Video Retrieval (TVR) is essential in video platforms. Dense retrieval with dual-modality encoders leads in accuracy, but its computation and storage scale poorly with corpus size. Thus, real-time large-scale applications adopt…
Modern video retrieval systems are expected to handle diverse tasks ranging from corpus-level retrieval, fine-grained moment localization to flexible multimodal querying. Specialized architectures achieve strong retrieval performance by…
Vision-Language Models (VLMs) have advanced rapidly within the unified Transformer architecture, yet their deployment on resource-constrained devices remains challenging due to high computational complexity. While pruning has emerged as an…
Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While efficient, they discard fine-grained, local evidence critical for dense retrieval…
Large multimodal models (LMMs) often suffer from severe inference inefficiency due to the large number of visual tokens introduced by image encoders. While recent token compression methods, such as pruning and merging, have shown promise in…
Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and…
Recent advances in vision-language models have demonstrated remarkable performance across diverse multi-modal tasks, including document question answering that leverages structured visual cues from text, tables, and figures. However, unlike…