Related papers: Multi-granularity Generator for Temporal Action Pr…
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…
Most state-of-the-art action localization systems process each action proposal individually, without explicitly exploiting their relations during learning. However, the relations between proposals actually play an important role in action…
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…
Accurately locating the start and end time of an action in untrimmed videos is a challenging task. One of the important reasons is the boundary of action is not highly distinguishable, and the features around the boundary are difficult to…
Temporal action localization in untrimmed videos is an important but difficult task. Difficulties are encountered in the application of existing methods when modeling temporal structures of videos. In the present study, we developed a novel…
Temporal action localization aims at localizing action instances from untrimmed videos. Existing works have designed various effective modules to precisely localize action instances based on appearance and motion features. However, by…
Future prediction, especially in long-range videos, requires reasoning from current and past observations. In this work, we address questions of temporal extent, scaling, and level of semantic abstraction with a flexible multi-granular…
Video temporal character grouping locates appearing moments of major characters within a video according to their identities. To this end, recent works have evolved from unsupervised clustering to graph-based supervised clustering. However,…
Point-level supervised temporal action localization (PTAL) aims at recognizing and localizing actions in untrimmed videos where only a single point (frame) within every action instance is annotated in training data. Without temporal…
We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normalized cuts algorithm.…
This technical report presents the 3rd winning solution for MTVG, a new task introduced in the 4-th Person in Context (PIC) Challenge at ACM MM 2022. MTVG aims at localizing the temporal boundary of the step in an untrimmed video based on a…
Video affective understanding, which aims to predict the evoked expressions by the video content, is desired for video creation and recommendation. In the recent EEV challenge, a dense affective understanding task is proposed and requires…
Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this…
Detecting activities in untrimmed videos is an important but challenging task. The performance of existing methods remains unsatisfactory, e.g., they often meet difficulties in locating the beginning and end of a long complex action. In…
We present a Temporal Context Network (TCN) for precise temporal localization of human activities. Similar to the Faster-RCNN architecture, proposals are placed at equal intervals in a video which span multiple temporal scales. We propose a…
Today's VidSGG models are all proposal-based methods, i.e., they first generate numerous paired subject-object snippets as proposals, and then conduct predicate classification for each proposal. In this paper, we argue that this prevalent…
Temporal Video Grounding (TVG) aims to localize temporal moments in an untrimmed video that semantically correspond to given natural language queries. Recently, Graph Convolutional Networks (GCN) have been widely adopted in TVG to model…
We address temporal action localization in untrimmed long videos. This is important because videos in real applications are usually unconstrained and contain multiple action instances plus video content of background scenes or other…
Video-based person re-identification (re-ID) is an important research topic in computer vision. The key to tackling the challenging task is to exploit both spatial and temporal clues in video sequences. In this work, we propose a novel…
Temporal action localization has long been researched in computer vision. Existing state-of-the-art action localization methods divide each video into multiple action units (i.e., proposals in two-stage methods and segments in one-stage…