Papers › Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs

Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs

13 Jun 2019ICCV 2019 10arXiv:1906.05910archive 2025-07-28

Lei Wang, Piotr Koniusz, Du. Q. Huynh

In this paper, we revive the use of old-fashioned handcrafted video representations for action recognition and put new life into these techniques via a CNN-based hallucination step. Despite of the use of RGB and optical flow frames, the I3D model (amongst others) thrives on combining its output with the Improved Dense Trajectory (IDT) and extracted with its low-level video descriptors encoded via Bag-of-Words (BoW) and Fisher Vectors (FV). Such a fusion of CNNs and handcrafted representations is time-consuming due to pre-processing, descriptor extraction, encoding and tuning parameters. Thus, we propose an end-to-end trainable network with streams which learn the IDT-based BoW/FV representations at the training stage and are simple to integrate with the I3D model. Specifically, each stream takes I3D feature maps ahead of the last 1D conv. layer and learns to `translate' these maps to BoW/FV representations. Thus, our model can hallucinate and use such synthesized BoW/FV representations at the testing stage. We show that even features of the entire I3D optical flow stream can be hallucinated thus simplifying the pipeline. Our model saves 20-55h of computations and yields state-of-the-art results on four publicly available datasets.

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 RecognitionHallucinationOptical Flow EstimationScene Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Charades HAF+BoW/FV/OFF halluc. +MSK×8/PN MAP 43.1 #24 of 49 Archive leaderboard report
Action Recognition HMDB-51 HAF+BoW/FV halluc Average accuracy of 3 splits 82.48 #15 of 77 Archive leaderboard report
Scene Recognition YUP++ HAF+BoW/FV halluc. Accuracy (%) 92.6 #3 of 5 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