2021 · 59 citations · 44 references
ComputingComputer ScienceComputer VisionFeature EngineeringNatural Language ProcessingMultimodal InteractionObject DetectionObject RecognitionRepresentation LearningScene UnderstandingVideo AnalysisFeature FusionMultimodal Feature FusionMultimodal FusionSpatiotemporal Feature ExtractionVideo ClassificationVideo RelationsVideo Scene UnderstandingVisual Relationship Detection
Video Visual Relation Detection (VidVRD) aims to semantically describe the dynamic interactions across visual concepts localized in a video in the form of subject, predicate, object. It can help to mitigate the semantic gap between vision and language in video understanding, thus receiving increasing attention in multimedia communities. Existing efforts primarily leverage the multimodal/spatio-temporal feature fusion to augment the representation of object trajectories as well as their interactions and formulate the prediction of predicates as a multi-class classification task. Despite their effectiveness, existing models ignore the severe long-tailed bias in VidVRD datasets. As a result, the models' prediction will be easily biased towards the popular head predicates (e.g., next-to and in-front-of), thus leading to poor generalizability.
44
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Accurate Scale Estimation for Robust Visual Tracking
Martin Danelljan, G Hager, Fahad Shahbaz Khan et al. · 2014 · 2.2K citations · Full text
Image retrieval using scene graphs
Justin Johnson, Ranjay Krishna, Michael Stark et al. · 2015 · 1.1K citations
Unbiased Scene Graph Generation From Biased Training
Kaihua Tang, Yulei Niu, Jianqiang Huang et al. · 2020 · 728 citations