SOTA: Spike-Navigated Optimal TrAnsport Saliency Region Detection in Composite-bias Videos
Authors: Wenxuan Liu, Yao Deng, Kang Chen, Xian Zhong, Zhaofei Yu, Tiejun Huang
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on real and synthetic datasets demonstrate that SOTA outperforms existing methods by eliminating composite noise bias. |
| Researcher Affiliation | Academia | Wenxuan Liu1,2 , Yao Deng2 , Kang Chen1 , Xian Zhong2, , Zhaofei Yu3,1 and Tiejun Huang1 1State Key Laboratory for Multimedia Information Processing, Peking University 2Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology 3Institute for Artificial Intelligence, Peking University EMAIL, EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper describes the proposed method using descriptive text and mathematical formulations but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | Our code and dataset will be released at https: //github.com/lwxfight/sota. |
| Open Datasets | Yes | To evaluate the effectiveness of our proposed SOTA framework, we construct a bio-inspired video saliency detection dataset, SPIKE-DAVIS [Perazzi et al., 2016], following prior works on related tasks [Zhang et al., 2022]. ... SVS dataset, captured using a spike camera with spatial resolution 250 400 and temporal resolution of 20,000 Hz [Zhu et al., 2024a] |
| Dataset Splits | Yes | SVS dataset, ... consists of 130 sequences. Of these, 100 are used for training (24 highcondition, 76 low-condition) and 30 for validation (8 highcondition, 22 low-condition). |
| Hardware Specification | Yes | All experiments are conducted on the Py Torch platform with an NVIDIA RTX 4090 24GB GPU. |
| Software Dependencies | No | The paper mentions 'Py Torch platform' but does not specify a version number for PyTorch or any other software dependencies. |
| Experiment Setup | Yes | We optimize SOTA using the Adam optimizer [Kingma and Ba, 2015] with an initial learning rate of 2e 4 and a weight decay of 2e 5. The batch size is 2, and input images are resized to 256 256. |