Related papers: AA-RMVSNet: Adaptive Aggregation Recurrent Multi-v…

Recently, recurrent neural networks have become state-of-the-art in acoustic modeling for automatic speech recognition. The long short-term memory (LSTM) units are the most popular ones. However, alternative units like gated recurrent unit…

Although Recurrent Neural Network (RNN) has been a powerful tool for modeling sequential data, its performance is inadequate when processing sequences with multiple patterns. In this paper, we address this challenge by introducing a novel…

In computer vision domain, how to fast and accurately perform multiview stereo (MVS) is still a challenging problem. In this paper we present a fast yet accurate method for 3D dense reconstruction, called AMHMVS, built on the PatchMatch…

Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, existing methods lack flexible adaptivity, leading to irreversible detail loss and…

Recent deep multi-view stereo (MVS) methods have widely incorporated transformers into cascade network for high-resolution depth estimation, achieving impressive results. However, existing transformer-based methods are constrained by their…

We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…

Long Short-Term Memory (LSTM) is a prominent recurrent neural network for extracting dependencies from sequential data such as time-series and multi-view data, having achieved impressive results for different visual recognition tasks. A…

We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches. This is in contrast to previous person re-id works, which rely on…

Deep learning-based multi-view stereo has emerged as a powerful paradigm for reconstructing the complete geometrically-detailed objects from multi-views. Most of the existing approaches only estimate the pixel-wise depth value by minimizing…

With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly…

Recurrent neural networks (RNNs) have shown excellent performance in processing sequence data. However, they are both complex and memory intensive due to their recursive nature. These limitations make RNNs difficult to embed on mobile…

Recent learning-based inpainting algorithms have achieved compelling results for completing missing regions after removing undesired objects in videos. To maintain the temporal consistency among the frames, 3D spatial and temporal…

Autoregressive (AR) diffusion enables streaming, interactive long-video generation by producing frames causally, yet maintaining coherence over minute-scale horizons remains challenging due to accumulated errors, motion drift, and content…

Recent semantic segmentation research has increasingly moved toward stronger context modeling, dense attention, and transformer-based architectures. Although these models achieve impressive performance, classical CNN-based segmentation…

The Large Vision-Language Model (LVLM) integrates computer vision and natural language processing techniques, offering substantial application potential. However, these models demand extensive resources during inference. Adaptive attention…

Active vision is inherently attention-driven: The agent actively selects views to attend in order to fast achieve the vision task while improving its internal representation of the scene being observed. Inspired by the recent success of…

Dynamic Vision Sensors (DVSs) asynchronously stream events in correspondence of pixels subject to brightness changes. Differently from classic vision devices, they produce a sparse representation of the scene. Therefore, to apply standard…

Current methods for video analysis often extract frame-level features using pre-trained convolutional neural networks (CNNs). Such features are then aggregated over time e.g., by simple temporal averaging or more sophisticated recurrent…

Stereo matching is a fundamental building block for many vision and robotics applications. An informative and concise cost volume representation is vital for stereo matching of high accuracy and efficiency. In this paper, we present a novel…

Transformer-based methods have demonstrated impressive performance in low-level visual tasks such as Image Super-Resolution (SR). However, its computational complexity grows quadratically with the spatial resolution. A series of works…