Supervised Set-to-Set Hashing in Visual Recognition
Authors: I-Hong Jhuo
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on two visual retrieval datasets show unambiguously that our setto-set hashing framework outperforms prior methods that do not take the set-to-set search setting. |
| Researcher Affiliation | Industry | I-Hong Jhuo CODAIT, IBM ihjhuo@gmail.com |
| Pseudocode | Yes | Algorithm 1 Image Set Hashing |
| Open Source Code | No | The paper states, 'For the competing techniques, we adopted the publicly released codes of SH, KLSH, KSH and HER in our experiments.', but does not provide any link or statement regarding the open-sourcing of the code for their proposed method. |
| Open Datasets | Yes | We evaluate the effectiveness of the proposed Image Set Hashing (ISH) method on two well-known benchmarks, CIFAR-10 and TV-series, i.e., Big Bang Theory. ... The Big Bang Theory (BBT) video (image set) benchmark 1 was collected by [Bauml et al., 2013] and contains in 3341 face videos from 1-6 episodes of season one. 1https://cvhci.anthropomatik.kit.edu/~baeuml/datasets.html |
| Dataset Splits | No | For the CIFAR-10 dataset: 'we uniformly and randomly sample images from each category to form a total of 195 image sets, each of which contains about 25-50 images for the training process (q and r two parts), 100 image sets as query in testing and 1577 image sets for the testing database'. For TV-series: 'we have 150 image sets for q and r two parts in the training process, respectively. For query in testing, we use 100 image sets and the remaining image sets for database.' The paper describes training and testing sets but does not explicitly mention a separate validation set split. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory, or cloud instance types) used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'publicly released codes of SH, KLSH, KSH and HER' for comparative experiments but does not specify any software names with version numbers for its own implementation or dependencies. |
| Experiment Setup | Yes | For feature representation, each image is represented as a 512-dimensional GIST feature vector. ... We vary the number of hash bits from 8 to 128 bits. |