Jiajun Song
Orcid: 0009-0005-5439-0176
According to our database1,
Jiajun Song
authored at least 18 papers
between 2021 and 2024.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2024
IEEE Trans. Ind. Informatics, April, 2024
Sensors, February, 2024
Towards Food Image Retrieval via Generalization-Oriented Sampling and Loss Function Design.
ACM Trans. Multim. Comput. Commun. Appl., January, 2024
Microelectron. J., January, 2024
IEEE Trans. Image Process., 2024
Out-of-distribution generalization via composition: a lens through induction heads in Transformers.
CoRR, 2024
Dataset and Benchmark for Urdu Natural Scenes Text Detection, Recognition and Visual Question Answering.
Proceedings of the Document Analysis and Recognition - ICDAR 2024 - 18th International Conference, Athens, Greece, August 30, 2024
A Joint Approach to Local Updating and Gradient Compression for Efficient Asynchronous Federated Learning.
Proceedings of the Euro-Par 2024: Parallel Processing, 2024
2023
Transcriptional correlates of frequency-dependent brain functional activity associated with symptom severity in degenerative cervical myelopathy.
NeuroImage, December, 2023
A Time-Domain Reconfigurable Second-Order Noise Shaping ADC With Single Fan-Out Gated Delay Cells.
IEEE Trans. Very Large Scale Integr. Syst., June, 2023
IEEE Trans. Circuits Syst. I Regul. Pap., May, 2023
Ingredient Prediction via Context Learning Network With Class-Adaptive Asymmetric Loss.
IEEE Trans. Image Process., 2023
CoRR, 2023
Proceedings of the 31st ACM International Conference on Multimedia, 2023
Proceedings of the IEEE INFOCOM 2023, 2023
2022
Proceedings of the 5th IEEE International Conference on Multimedia Information Processing and Retrieval, 2022
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones Is Enough.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022
2021
Rethinking Ranking-based Loss Functions: Only Penalizing Negative Instances before Positive Ones is Enough.
CoRR, 2021