Related papers: Learning Generalized Spatial-Temporal Deep Feature…
No-reference video quality assessment (NR-VQA) for gaming videos is challenging due to limited human-rated datasets and unique content characteristics including fast motion, stylized graphics, and compression artifacts. We present MTL-VQA,…
We propose a self-supervised learning approach for videos that learns representations of both the RGB frames and the accompanying audio without human supervision. In contrast to images that capture the static scene appearance, videos also…
Video-Language Pre-training models have recently significantly improved various multi-modal downstream tasks. Previous dominant works mainly adopt contrastive learning to achieve global feature alignment across modalities. However, the…
In the field of action recognition, video clips are always treated as ordered frames for subsequent processing. To achieve spatio-temporal perception, existing approaches propose to embed adjacent temporal interaction in the convolutional…
High-quality video inpainting that completes missing regions in video frames is a promising yet challenging task. State-of-the-art approaches adopt attention models to complete a frame by searching missing contents from reference frames,…
Compression has been an important research topic for many decades, to produce a significant impact on data transmission and storage. Recent advances have shown a great potential of learning image and video compression. Inspired from related…
Weakly supervised temporal video grounding aims to localize query-relevant segments in untrimmed videos using only video-sentence pairs, without requiring ground-truth segment annotations that specify exact temporal boundaries. Recent…
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…
Due to the resource-intensive nature of training vision-language models on expansive video data, a majority of studies have centered on adapting pre-trained image-language models to the video domain. Dominant pipelines propose to tackle the…
We leverage unsupervised learning of depth, egomotion, and camera intrinsics to improve the performance of single-image semantic segmentation, by enforcing 3D-geometric and temporal consistency of segmentation masks across video frames. The…
Two-stream convolutional networks have shown strong performance in video action recognition tasks. The key idea is to learn spatiotemporal features by fusing convolutional networks spatially and temporally. However, it remains unclear how…
No-reference video quality assessment (NR-VQA) estimates perceptual quality without a reference video, which is often challenging. While recent techniques leverage saliency or transformer attention, they merely address global context of the…
This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal…
Video compression performance is closely related to the accuracy of inter prediction. It tends to be difficult to obtain accurate inter prediction for the local video regions with inconsistent motion and occlusion. Traditional video coding…
Video object segmentation is challenging due to the factors like rapidly fast motion, cluttered backgrounds, arbitrary object appearance variation and shape deformation. Most existing methods only explore appearance information between two…
Text-to-video generation aims to produce a video based on a given prompt. Recently, several commercial video models have been able to generate plausible videos with minimal noise, excellent details, and high aesthetic scores. However, these…
We present Buffer Anytime, a framework for estimation of depth and normal maps (which we call geometric buffers) from video that eliminates the need for paired video--depth and video--normal training data. Instead of relying on large-scale…
Recent works in video quality assessment (VQA) typically employ monolithic models that typically predict a single quality score for each test video. These approaches cannot provide diagnostic, interpretable feedback, offering little insight…
Video summarization aims to automatically generate a diverse and concise summary which is useful in large-scale video processing. Most of the methods tend to adopt self-attention mechanism across video frames, which fails to model the…
Neural View Synthesis (NVS), such as NeRF and 3D Gaussian Splatting, effectively creates photorealistic scenes from sparse viewpoints, typically evaluated by quality assessment methods like PSNR, SSIM, and LPIPS. However, these…