Multi-Objective Self-Paced Learning

Authors: Hao Li, Maoguo Gong, Deyu Meng, Qiguang Miao

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on matrix factorization and action recognition demonstrate the superiority of the proposed method against the existing issues in current SPL research.
Researcher Affiliation Academia 1Key Laboratory of Intelligent Perception and Image Understanding, Xidian University, Xi an, China 2School of Mathematics and Statistics, Xi an Jiaotong University, Xi an, China 3School of Computer Science and Technology, Xidian University, Xi an, China omegalihao@gmail.com, gong@ieee.org, dymeng@mail.xjtu.edu.cn, qgmiao@mail.xidian.edu.cn
Pseudocode Yes Algorithm 1 Algorithm of Multi-objective Self-paced Learning.
Open Source Code No No explicit statement about providing open-source code or a link to a code repository was found.
Open Datasets Yes Hollywood2 was collected from 69 different Hollywood movies (Marszalek, Laptev, and Schmid 2009).
Dataset Splits Yes Hollywood2 was collected from 69 different Hollywood movies (Marszalek, Laptev, and Schmid 2009). It contains 1707 videos belonging to 12 actions, splitting into a training set (823 videos) and a test set (884 videos).
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments were provided.
Software Dependencies No No specific software dependencies with version numbers were explicitly mentioned (e.g., Python 3.x, PyTorch 1.x).
Experiment Setup No No specific hyperparameters (e.g., learning rate, batch size, epochs) or detailed training configurations were explicitly provided.