External resources list based on suggestions from TRECVID participants
|
NOTE: Any mention of commercial products within NIST web pages is for information only; it does not imply recommendation or endorsement by NIST. Please email TRECVID with suggestions for additional resources. |
|||||
|---|---|---|---|---|---|
| Short name | Scope | URL | As of dd.mm.yy |
||
| FFMPEG | Basic Image and Video Processing | URL | 11.12.14 | ||
| KNIME | Visualisation, Rapid Prototyping, Workflow Generation | URL | 11.12.14 | ||
| OpenCV | Image Processing, Machine Learning | URL | 11.12.14 | ||
| openSMILE | Audio Feature Extraction | URL | 11.12.14 | ||
| PostgreSQL | Database for large data collections | URL | 11.12.14 | ||
| Python Image Library/Pillow | Rapid Prototyping, Image Processing | URL | 11.12.14 | ||
| Scilab | Visualisation, Rapid Prototyping, High-level mathematics | URL | 11.12.14 | ||
| VLFEAT | Feature extraction like SIFT, and MSER | URL | 11.12.14 | ||
| WEKA | Data Mining, Machine Learning | URL | 11.12.14 | ||
| Zero-Example Video Search | open source baseline system | URL | 06.06.17 | ||
| Docker image tools for development | To support INS task using Docker images to simplify development of algorithms Contact the author Robert Manthey if you have questions | URL | 03.05.18 | ||
| Frame-level CNN features for IACC.3 dataset | Applied at 2018 for the Ad-hoc Video Search (AVS) task by the RUCMM team (best runs) Contact the author Xirong Li if you have questions | URL | 11.09.18 | ||
| Code and model for "Peeking into the Future: Predicting Future Person Activities and Locations in Videos", Liang et al, CVPR 2019 | End-to-End neural network model that deciphers human behaviors to predict their future paths/trajectories and their future activities jointly from videos Contact the author Junwei Liang if you have questions | URL | 12.03.19 | ||
| Out-of-the-box code and models for CMU's object detection and tracking system for surveillance videos. Tensorflow based | Used in the winning entry on the ActEV leaderboard (INF/MUDSML) Contact the author Junwei Liang if you have questions | URL | 12.03.19 | ||
| W2VV++ model | A fully deep learning solution for ad-hoc video search Contact the author Xirong Li if you have questions | URL | 12.09.19 | ||
| V3C1 Dataset Analysis | Analysis data of the Vimeo Creative Commons Collection (V3C1) dataset Contact the authors Klaus Schoeffmann and Luca Rossetto if you have questions | URL | 12.30.19 | ||
| V3C2 Dataset Analysis | Analysis data of the Vimeo Creative Commons Collection (V3C2) dataset Contact the authors Klaus Schoeffmann and Luca Rossetto if you have questions | URL | 1.4.22 | ||
| V3C1 & V3C2 ASR | Vimeo Creative Commons Collection (V3C) Whisper Transcripts Contact the author Luca Rossetto if you have questions | URL Paper | 11.4.22 | ||
| SOMHunter | video search and retrieval engine Contact the author Miroslav Kratochvíl if you have questions | URL | 1.4.22 | ||
| vitrivr | video search and retrieval engine Contact the author Luca Rossetto if you have questions | URL | 1.4.22 | ||
| Events Zero Shot Classification | EURECOM approach for the TRECVID VSUM 2021 task Contact the authors Raphael Troncy, and Alison Reboud if you have questions | URL | 1.7.22 | ||
| V3C1-Pseudo-Caption (V3C1-PC) | auto-generated video description dataset Contact the authors Xirong Li if you have questions | URL | 3.1.23 | ||
| CLIP and BLIP-2 features (AVS queries) | The query and frame-level clip features of both CLIP and BLIP2 models on IACC.3, V3C1, V3C2 and all the AVS queries Contact the authors WU Jiaxin if you have questions | URL | 11.15.23 | ||
News magazine, science news, news reports, documentaries, educational programming, and archival video
TV Episodes
Airport Security Cameras & Activity Detection
Video collections from News, Sound & Vision, Internet Archive,
Social Media, BBC Eastenders