Object-Centric Spatio-Temporal Activity Detection and Recognition

Run-ID (AD/AOD) Submission AD AOD Note 283/284 IBM_E2E 0.8396338981 0.8433932966 S1: Baseline entries of IBM system for eval-1a 330/331 IBM_E2E_ALL (TRN3-TRN3 filtered ) 0.7716112433 0.7928942585 S2: Baseline entries of IBM system for eval-1a, for all 19 activities. 351/352 IBM_E2E_ALL (unfiltered) 0.7706395834 0.7932181452 S2, but with unfiltered results 355/356 IBM_E2E_ALL (filtered & merged) 0.7762367494 0.7958497241 S2 with a merging algorithm 371/IBM_E2E_ALL (TRN16) 0.7953969555 S3: TRN 16 instead of TRN 3. 397/398 IBM_E2E_ALL_New (unfiltered) 0.7589621185 0.7785331614 S4: S2 + new turning algorithm 436/438 IBM_E2E_ALL_New (unfiltered + Ensemble) 0.7189424498 0.7629197006 S5: S2 + newly trained activity classifiers 453/440 IBM_E2E_ALL_New (unfiltered + Ensemble + LR-turns) 0.7087156227 0.7520320714 S6: Our winning entries, S4 + S5.

[1]  Fabio Tozeto Ramos,et al.  Simple online and realtime tracking , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[2]  Jonathan G. Fiscus,et al.  TRECVID 2018: Benchmarking Video Activity Detection, Video Captioning and Matching, Video Storytelling Linking and Video Search , 2018, TRECVID.

[3]  Kate Saenko,et al.  R-C3D: Region Convolutional 3D Network for Temporal Activity Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[4]  Cordelia Schmid,et al.  Action Tubelet Detector for Spatio-Temporal Action Localization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[5]  Rogério Schmidt Feris,et al.  A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection , 2016, ECCV.