Dialog-based Interactive Image Retrieval

Authors: Xiaoxiao Guo, Hui Wu, Yu Cheng, Steven Rennie, Gerald Tesauro, Rogerio Feris

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on both simulated and real-world data show that 1) our proposed learning framework achieves better accuracy than other supervised and reinforcement learning baselines and 2) user feedback based on natural language rather than pre-specified attributes leads to more effective retrieval results, and a more natural and expressive communication interface.
Researcher Affiliation Industry Xiaoxiao Guo IBM Research AI xiaoxiao.guo@ibm.com Hui Wu IBM Research AI wuhu@us.ibm.com Yu Cheng IBM Research AI chengyu@us.ibm.com Steven Rennie Fusemachines Inc. srennie@gmail.com Gerald Tesauro IBM Research AI gtesauro@us.ibm.com Rogerio Schmidt Feris IBM Research AI rsferis@us.ibm.com
Pseudocode No The paper describes the model architecture and training process in detail but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper mentions 'The project website is at: www.spacewu.com/posts/fashion-retrieval/' in a footnote. This is a project website, not an explicit statement that the source code for the methodology is openly available or a direct link to a code repository (e.g., GitHub).
Open Datasets Yes All experiments were performed on the Shoes dataset [53], with the same training and testing data split for all retrieval methods and for training the user simulator.
Dataset Splits No The paper specifies '10, 000 database images were used during training, and 4, 658 images for testing,' but does not explicitly mention a separate validation split or its size/proportion.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types, memory) used to run the experiments.
Software Dependencies No The paper mentions deep learning models and architectures such as 'Res Net-101 [44]' and 'long short-term memory network (LSTM),' but it does not specify any software dependencies with version numbers (e.g., Python 3.8, PyTorch 1.9).
Experiment Setup No For details on architectural configurations, parameter settings, baseline implementation, please refer to Appendix D.