Related papers: Tencent AVS: A Holistic Ads Video Dataset for Mult…
The recent works on Video Object Segmentation achieved remarkable results by matching dense semantic and instance-level features between the current and previous frames for long-time propagation. Nevertheless, global feature matching…
Video Instance Segmentation (VIS) jointly tackles multi-object detection, tracking, and segmentation in video sequences. In the past, VIS methods mirrored the fragmentation of these subtasks in their architectural design, hence missing out…
Audio-Visual Segmentation (AVS) aims to extract the sounding object from a video frame, which is represented by a pixel-wise segmentation mask for application scenarios such as multi-modal video editing, augmented reality, and intelligent…
We address the problem of highlight detection from a 360 degree video by summarizing it both spatially and temporally. Given a long 360 degree video, we spatially select pleasantly-looking normal field-of-view (NFOV) segments from unlimited…
In Video Instance Segmentation (VIS), current approaches either focus on the quality of the results, by taking the whole video as input and processing it offline; or on speed, by handling it frame by frame at the cost of competitive…
Temporal Action Detection (TAD) is an essential and challenging topic in video understanding, aiming to localize the temporal segments containing human action instances and predict the action categories. The previous works greatly rely upon…
As the most fundamental scene understanding tasks, object detection and segmentation have made tremendous progress in deep learning era. Due to the expensive manual labeling cost, the annotated categories in existing datasets are often…
Modern approaches have proved the huge potential of addressing semantic segmentation as a mask classification task which is widely used in instance-level segmentation. This paradigm trains models by assigning part of object queries to…
We propose an Explicit Conditional Multimodal Variational Auto-Encoder (ECMVAE) for audio-visual segmentation (AVS), aiming to segment sound sources in the video sequence. Existing AVS methods focus on implicit feature fusion strategies,…
Audio-Visual Segmentation (AVS) aims to achieve pixel-level localization of sound sources in videos, while Audio-Visual Semantic Segmentation (AVSS), as an extension of AVS, further pursues semantic understanding of audio-visual scenes.…
In recent years, there has been remarkable progress in supervised image segmentation. Video segmentation is less explored, despite the temporal dimension being highly informative. Semantic labels, e.g. that cannot be accurately detected in…
TASED-Net is a 3D fully-convolutional network architecture for video saliency detection. It consists of two building blocks: first, the encoder network extracts low-resolution spatiotemporal features from an input clip of several…
Amodal segmentation and amodal content completion require using object priors to estimate occluded masks and features of objects in complex scenes. Until now, no data has provided an additional dimension for object context: the possibility…
Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using information from visible tokens. However, a key challenge in…
We present the 2017 DAVIS Challenge on Video Object Segmentation, a public dataset, benchmark, and competition specifically designed for the task of video object segmentation. Following the footsteps of other successful initiatives, such as…
Referring video object segmentation (RVOS) has recently generated great popularity in computer vision due to its widespread applications. Existing RVOS setting contains elaborately trimmed videos, with text-referred objects always appearing…
Audiovisual segmentation (AVS) aims to identify visual regions corresponding to sound sources, playing a vital role in video understanding, surveillance, and human-computer interaction. Traditional AVS methods depend on large-scale…
Referring Video Object Segmentation (RVOS) aims to segment target objects in video sequences based on natural language descriptions. While recent advances in Multi-modal Large Language Models (MLLMs) have improved RVOS performance through…
Video event localization tasks include temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL). Existing methods tend to over-specialize on individual tasks, neglecting the equal importance…
Temporal Action Segmentation (TAS) requires dividing videos into action segments, yet the vast space of activities and alternative breakdowns makes collecting comprehensive datasets infeasible. Existing methods remain limited to closed…