Complex Event Detection using Semantic Saliency and Nearly-Isotonic SVM
Authors: Xiaojun Chang, Yi Yang, Eric Xing, Yaoliang Yu
ICML 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct extensive experiments on three real-world video datasets and confirm the effectiveness of the proposed approach. |
| Researcher Affiliation | Academia | Xiaojun Chang CXJ273@GMAIL.COM Yi Yang YEE.I.YANG@GMAIL.COM Centre for Quantum Computation and Intelligent Systems, University of Technology Sydney, Sydney, Australia Eric P. Xing EPXING@CS.CMU.EDU Yao-Liang Yu YAOLIANG@CS.CMU.EDU Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA, USA |
| Pseudocode | Yes | Algorithm 1: Proximal Gradient for NI-SVM |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of the described methodology. |
| Open Datasets | Yes | Datasets We test on three real event detection datasets: MED14: The TRECVID MEDTest 2014 dataset (NIST, 2014)... MED13 (NIST, 2013)... CCVsub: The official Columbia Consumer Video dataset (Jiang et al., 2011) |
| Dataset Splits | Yes | MED14: ...contains approximately 100 positive training exemplars per event, and all events share ( 5000) negative training exemplars. The test set has approximately 23,000 videos. ... For each event we use its own training data as positive and all other training data as negative, totaling 4,659 training videos and 4,658 testing videos. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions using a 'CNN architecture in (Simonyan & Zisserman, 2015)' but does not specify software dependencies with version numbers (e.g., specific libraries, frameworks, or programming language versions). |
| Experiment Setup | Yes | The regularization constants λ and γ are selected using crossvalidation from the range {10 4, 10 3, . . . , 103, 104}. |