Papers › Representation Learning on Visual-Symbolic Graphs for Video Understanding

Representation Learning on Visual-Symbolic Graphs for Video Understanding

17 May 2019ECCV 2020 8arXiv:1905.07385archive 2025-07-28

Effrosyni Mavroudi, Benjamín Béjar Haro, René Vidal

Events in natural videos typically arise from spatio-temporal interactions between actors and objects and involve multiple co-occurring activities and object classes. To capture this rich visual and semantic context, we propose using two graphs: (1) an attributed spatio-temporal visual graph whose nodes correspond to actors and objects and whose edges encode different types of interactions, and (2) a symbolic graph that models semantic relationships. We further propose a graph neural network for refining the representations of actors, objects and their interactions on the resulting hybrid graph. Our model goes beyond current approaches that assume nodes and edges are of the same type, operate on graphs with fixed edge weights and do not use a symbolic graph. In particular, our framework: a) has specialized attention-based message functions for different node and edge types; b) uses visual edge features; c) integrates visual evidence with label relationships; and d) performs global reasoning in the semantic space. Experiments on challenging video understanding tasks, such as temporal action localization on the Charades dataset, show that the proposed method leads to state-of-the-art performance.

PaperPDFConference PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action ClassificationAction DetectionAction LocalizationAction SegmentationGeneral ClassificationGraph Neural NetworkRepresentation LearningTemporal Action LocalizationVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Detection Charades I3D + biGRU + VS-ST-MPNN mAP 23.7 #10 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Graph Neural Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections