2023 · 35 citations · 63 references
ComputingComputer ScienceComputer VisionFeature EngineeringLocalizationAction RecognitionFeature DescriptionMotion EstimationScene UnderstandingVideo AnalysisVisual LocalizationAction SegmentationFeature Pyramid NetworksRetrievalSegmentationSpatiotemporal Feature ExtractionTemporal FusionText Feature Fusion
While large-scale image-text pretrained models such as CLIP have been used for multiple video-level tasks on trimmed videos, their use for temporal localization in untrimmed videos is still a relatively unexplored task. We design a new approach for this called UnLoc, which uses pretrained image and text towers, and feeds tokens to a video-text fusion model. The output of the fusion module are then used to construct a feature pyramid in which each level connects to a head to predict a per-frame relevancy score and start/end time displacements. Unlike previous works, our architecture enables Moment Retrieval, Temporal Localization, and Action Segmentation with a single stage model, without the need for action proposals, motion based pretrained features or representation masking. Unlike specialized models, we achieve state of the art results on all three different localization tasks with a unified approach. Code is available at: https://github.com/google-research/scenic.
63
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2023 · 76.3K citations · Full text
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick et al. · 2017 · 28.7K citations
Focal Loss for Dense Object Detection
Tsung-Yi Lin, Priya Goyal, Ross Girshick et al. · 2017 · 25.7K citations