相关论文: Dynamic Weight-based Temporal Aggregation for Low-…

We propose Text-Aligned Speech Tokens with Multiple Layer-Aggregation (TASLA), which is a text-aligned speech tokenization framework that aims to address the problem that under a low-frame-rate and text-aligned regime, single-source speech…

Text-driven video moment retrieval (VMR) remains challenging due to limited capture of hidden temporal dynamics in untrimmed videos, leading to imprecise grounding in long sequences. Traditional methods rely on natural language queries…

Image diffusion models have been adapted for real-world video super-resolution to tackle over-smoothing issues in GAN-based methods. However, these models struggle to maintain temporal consistency, as they are trained on static images,…

Many tasks in video analysis and understanding boil down to the need for frame-based feature learning, aiming to encapsulate the relevant visual content so as to enable simpler and easier subsequent processing. While supervised strategies…

Restoring images from low-light data is a challenging problem. Most existing deep-network based algorithms are designed to be trained with pairwise images. Due to the lack of real-world datasets, they usually perform poorly when generalized…

Current Vision-Language-Action (VLA) models rely on fixed computational depth, expending the same amount of compute on simple adjustments and complex multi-step manipulation. While Chain-of-Thought (CoT) prompting enables variable…

Video denoising aims to recover high-quality frames from the noisy video. While most existing approaches adopt convolutional neural networks~(CNNs) to separate the noise from the original visual content, however, CNNs focus on local…

Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across…

Detecting temporal changes in geographical landscapes is critical for applications like environmental monitoring and urban planning. While remote sensing data is abundant, existing vision-language models (VLMs) often fail to capture…

Remote sensing image change detection (RSCD) is crucial for monitoring dynamic surface changes, with applications ranging from environmental monitoring to disaster assessment. While traditional CNN-based methods have improved detection…

Light field (LF) images containing information for multiple views have numerous applications, which can be severely affected by low-light imaging. Recent learning-based methods for low-light enhancement have some disadvantages, such as a…

Vision-language models (VLMs) exhibit remarkable zero-shot capabilities but struggle with distribution shifts in downstream tasks when labeled data is unavailable, which has motivated the development of Test-Time Adaptation (TTA) to improve…

Raw low light image enhancement (LLIE) has achieved much better performance than the sRGB domain enhancement methods due to the merits of raw data. However, the ambiguity between noisy to clean and raw to sRGB mappings may mislead the…

Several video understanding tasks, such as natural language temporal video grounding, temporal activity localization, and audio description generation, require "temporally dense" reasoning over frames sampled at high temporal resolution.…

The advent of Deep Neural Networks (DNNs) has driven remarkable progress in low-light image enhancement (LLIE), with diverse architectures (e.g., CNNs and Transformers) and color spaces (e.g., sRGB, HSV, HVI) yielding impressive results.…

Low signal-to-noise ratio videos -- such as those from underwater sonar, ultrasound, and microscopy -- pose significant challenges for computer vision models, particularly when paired clean imagery is unavailable. We present Spatiotemporal…

Low-light image enhancement is a challenging low-level computer vision task because after we enhance the brightness of the image, we have to deal with amplified noise, color distortion, detail loss, blurred edges, shadow blocks and halo…

The remastering of vintage film comprises of a diversity of sub-tasks including super-resolution, noise removal, and contrast enhancement which aim to restore the deteriorated film medium to its original state. Additionally, due to the…

We present a deep neural network to reduce coherent noise in three-dimensional quantitative phase imaging. Inspired by the cycle generative adversarial network, the denoising network was trained to learn a transform between two image…

Volumetric video relighting is essential for bringing captured performances into virtual worlds, but current approaches struggle to deliver temporally stable, production-ready results. Diffusion-based intrinsic decomposition methods show…