Papers › Visual Relationship Detection with Language Priors
Visual Relationship Detection with Language Priors
Cewu Lu, Ranjay Krishna, Michael Bernstein, Li Fei-Fei
Visual relationships capture a wide variety of interactions between pairs of objects in images (e.g. "man riding bicycle" and "man pushing bicycle"). Consequently, the set of possible relationships is extremely large and it is difficult to obtain sufficient training examples for all possible relationships. Because of this limitation, previous work on visual relationship detection has concentrated on predicting only a handful of relationships. Though most relationships are infrequent, their objects (e.g. "man" and "bicycle") and predicates (e.g. "riding" and "pushing") independently occur more frequently. We propose a model that uses this insight to train visual models for objects and predicates individually and later combines them together to predict multiple relationships per image. We improve on prior work by leveraging language priors from semantic word embeddings to finetune the likelihood of a predicted relationship. Our model can scale to predict thousands of types of relationships from a few examples. Additionally, we localize the objects in the predicted relationships as bounding boxes in the image. We further demonstrate that understanding relationships can improve content based image retrieval.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Scene Graph Generation | VRD | VRD | Recall@50 | 18.16 | #2 of 2 | Archive leaderboard | report |
| Visual Relationship Detection | VRD Phrase Detection | Lu et. al [[Lu et al.2016]] | R@100 | 17.03 | #7 of 7 | Archive leaderboard | report |
| Visual Relationship Detection | VRD Phrase Detection | Lu et. al [[Lu et al.2016]] | R@50 | 16.17 | #7 of 7 | Archive leaderboard | report |
| Visual Relationship Detection | VRD Predicate Detection | Lu et. al [[Lu et al.2016]] | R@100 | 47.87 | #6 of 7 | Archive leaderboard | report |
| Visual Relationship Detection | VRD Predicate Detection | Lu et. al [[Lu et al.2016]] | R@50 | 47.87 | #6 of 7 | Archive leaderboard | report |
| Visual Relationship Detection | VRD Relationship Detection | Lu et. al [[Lu et al.2016]] | R@100 | 14.70 | #8 of 8 | Archive leaderboard | report |
| Visual Relationship Detection | VRD Relationship Detection | Lu et. al [[Lu et al.2016]] | R@50 | 13.86 | #8 of 8 | 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.
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