Related papers: NVIDIA Nemotron Parse 1.1

Recent developments in Transformers have achieved notable strides in enhancing video comprehension. Nonetheless, the O($N^2$) computation complexity associated with attention mechanisms presents substantial computational hurdles when…

Acceleration of Convolutional Neural Network (CNN) on edge devices has recently achieved a remarkable performance in image classification and object detection applications. This paper proposes an efficient and scalable CNN-based SoC-FPGA…

We introduce a novel electro-optomechanic neural sensor for realizing ultra-compact neural recording probes that can detect and relay electrophysiology signals from within neural tissue. This technology addresses outstanding challenges…

The labeling cost of large number of bounding boxes is one of the main challenges for training modern object detectors. To reduce the dependence on expensive bounding box annotations, we propose a new semi-supervised object detection…

We introduce Long-VITA, a simple yet effective large multi-modal model for long-context visual-language understanding tasks. It is adept at concurrently processing and analyzing modalities of image, video, and text over 4K frames or 1M…

Vision-Language Models (VLMs) excel in diverse visual tasks but face challenges in document understanding, which requires fine-grained text processing. While typical visual tasks perform well with low-resolution inputs, reading-intensive…

Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline…

We launch EVA-02, a next-generation Transformer-based visual representation pre-trained to reconstruct strong and robust language-aligned vision features via masked image modeling. With an updated plain Transformer architecture as well as…

Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and so forth. Even advanced large vision-language models (LVLMs) with billions of parameters struggle to handle such tasks satisfactorily. To address…

When deploying neural networks in real-life situations, the size and computational effort are often the limiting factors. This is especially true in environments where big, expensive hardware is not affordable, like in embedded medical…

Multimodal Large Language Models (MLLMs) have shown strong performance in vision-language tasks, but their inference efficiency is severely limited by the exponential growth of visual tokens in complex scenarios such as high-resolution…

We introduce a new table detection and structure recognition approach named RobusTabNet to detect the boundaries of tables and reconstruct the cellular structure of each table from heterogeneous document images. For table detection, we…

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the large number of visual tokens, particularly in…

Both parametric and non-parametric approaches have demonstrated encouraging performances in the human parsing task, namely segmenting a human image into several semantic regions (e.g., hat, bag, left arm, face). In this work, we aim to…

In this report, we introduce Vintern-1B, a reliable 1-billion-parameters multimodal large language model (MLLM) for Vietnamese language tasks. By integrating the Qwen2-0.5B-Instruct language model with the InternViT-300M-448px visual model,…

We introduce NeuCo-Bench, a novel benchmark framework for evaluating (lossy) neural compression and representation learning in the context of Earth Observation (EO). Our approach builds on fixed-size embeddings that act as compact,…

A novel framework named Markov Clustering Network (MCN) is proposed for fast and robust scene text detection. MCN predicts instance-level bounding boxes by firstly converting an image into a Stochastic Flow Graph (SFG) and then performing…

Information extraction from documents is a ubiquitous first step in many business applications. During this step, the entries of various fields must first be read from the images of scanned documents before being further processed and…

We introduce a novel monocular visual odometry (VO) system, NeRF-VO, that integrates learning-based sparse visual odometry for low-latency camera tracking and a neural radiance scene representation for fine-detailed dense reconstruction and…

Vision-Language Model (VLM) based retrievers have advanced visual document retrieval (VDR) to impressive quality. They require the same multi-billion parameter encoder for both document indexing and query encoding, incurring high latency…