Khiem Le
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Khiem Le has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Thanh Duc Ngo
University of Information Technology, VNU-HCM, Ho Chi Minh, Vietnam and Vietnam National University Ho Chi Minh City, Ho Chi Minh, Vietnam
10 shared publications - Tien Do
University of Information Technology
9 shared publications - Thuyen Tran Doan
University of Information Technology
8 shared publications - Duy-Dinh Le
University of Information Technology
7 shared publications - Bao Tran Gia
University of Information Technology
4 shared publications - Tuong Bui Cong Khanh
University of Information Technology
3 shared publications
Latest Publications
- 11 July 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (6) , 403
Towards scalable and context-aware multimodal interactive video retrieval
- 11 July 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (6) , 403
Towards scalable and context-aware multimodal interactive video retrieval
- 12 December 2025
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 29 (2) , 463-481
Skeleton-guided artistic text recognition
- 12 December 2025
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 29 (2) , 463-481
Skeleton-guided artistic text recognition
- 26 April 2025
- Published by Springer Nature
- p. 206-218
A Hybrid Video Retrieval System Using CLIP and BEiT-3 for Enhanced Object and Contextual Understanding
- 26 April 2025
- Published by Springer Nature
- p. 206-218
A Hybrid Video Retrieval System Using CLIP and BEiT-3 for Enhanced Object and Contextual Understanding
- 26 April 2025
- Published by Springer Nature
- p. 195-205
Unveiling Peripheral Information: A Context-Aware Video Retrieval Approach
- 26 April 2025
- Published by Springer Nature
- p. 195-205
Unveiling Peripheral Information: A Context-Aware Video Retrieval Approach
- 26 April 2025
- Published by Springer Nature
- p. 167-180
Addressing Ambiguous Queries in Video Retrieval with Advanced Temporal Search
- 26 April 2025
- Published by Springer Nature
- p. 167-180
Addressing Ambiguous Queries in Video Retrieval with Advanced Temporal Search
- 1 January 2025
- Published by Springer Nature
- p. 318-325
NII-UIT at VBS2025: Multimodal Video Retrieval with LLM Integration and Dynamic Temporal Search
- 1 January 2025
- Published by Springer Nature
- p. 318-325
NII-UIT at VBS2025: Multimodal Video Retrieval with LLM Integration and Dynamic Temporal Search
- Open Access
- 22 June 2024
- Published by World Scientific Pub Co Pte Ltd in Vietnam Journal of Computer Science
- Vol. 11 (04) , 569-594
Key Information Extraction and Recognition from Rich Text Images
Key information extraction and recognition from rich text images are crucial for various applications. There are two main tasks involved in this process: Line Item Recognition (LIR) and Key Information Localization and Extraction (KILE). LIR aims at identifying and interpreting data line items in a document. The essential information in each line item is then classified or extracted, a task known as KILE. A widely used approach for this problem is sequence based, which relies on the generalization of a language model and requires a significant amount of training time. We present an effective and reliable solution to the problem by using RoBERTa, a transformer model trained on a large corpus, along with the LION optimizer to improve the training process. A comprehensive evaluation was conducted on two different benchmarks, emphasizing two different languages, English and Vietnamese. Experimental results on DocILE indicate that the proposed framework significantly improves the KILE task with a 7.24% increase in accuracy compared to the baseline and also enhances the correct recognition rate at the LIR stage. On MCOCR, the method achieved a Character Error Rate (CER) of 28.6%, which is competitive with the state-of-the-art on this dataset.
- 22 June 2024
- Published by World Scientific Pub Co Pte Ltd in Vietnam Journal of Computer Science
- Vol. 11 (04) , 569-594
Open AccessKey Information Extraction and Recognition from Rich Text Images
Key information extraction and recognition from rich text images are crucial for various applications. There are two main tasks involved in this process: Line Item Recognition (LIR) and Key Information Localization and Extraction (KILE). LIR aims at identifying and interpreting data line items in a document. The essential information in each line item is then classified or extracted, a task known as KILE. A widely used approach for this problem is sequence based, which relies on the generalization of a language model and requires a significant amount of training time. We present an effective and reliable solution to the problem by using RoBERTa, a transformer model trained on a large corpus, along with the LION optimizer to improve the training process. A comprehensive evaluation was conducted on two different benchmarks, emphasizing two different languages, English and Vietnamese. Experimental results on DocILE indicate that the proposed framework significantly improves the KILE task with a 7.24% increase in accuracy compared to the baseline and also enhances the correct recognition rate at the LIR stage. On MCOCR, the method achieved a Character Error Rate (CER) of 28.6%, which is competitive with the state-of-the-art on this dataset.
- Open Access
- 7 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1003-1010
Integrating Multiple Models For Effective Video Retrieval and Multi-stage Search
- 7 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1003-1010
Open AccessIntegrating Multiple Models For Effective Video Retrieval and Multi-stage Search
- Open Access
- 7 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 997-1002
Diverse Search Methods and Multi-Modal Fusion for High-Performance Video Retrieval
Querying events within extensive video datasets currently stands as a prominent research focus within the field of multimedia information retrieval. Achieving high-performance retrieval within such contexts necessitates the efficient extraction and effective storage of information from videos to expedite the retrieval process. These challenges become notably pronounced when handling substantial datasets. In this paper, we introduce a system tailored for event querying within video data. Our system is meticulously crafted to optimize information retrieval speed and to efficiently organize storage, harnessing the power of FAISS and ElasticSearch. It boasts the capability to process diverse forms of input information, including textual video descriptions, Optical Character Recognition (OCR) results, Automatic Speech Recognition (ASR) transcriptions, visually similar images, and details about objects within videos, encompassing aspects such as color and quantity. Moreover, our system can also extract information about the temporal sequence of events within videos—a particularly challenging task when extracting information from video frames. By amalgamating these various input types, our system delivers optimal results.
- 7 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 997-1002
Open AccessDiverse Search Methods and Multi-Modal Fusion for High-Performance Video Retrieval
Querying events within extensive video datasets currently stands as a prominent research focus within the field of multimedia information retrieval. Achieving high-performance retrieval within such contexts necessitates the efficient extraction and effective storage of information from videos to expedite the retrieval process. These challenges become notably pronounced when handling substantial datasets. In this paper, we introduce a system tailored for event querying within video data. Our system is meticulously crafted to optimize information retrieval speed and to efficiently organize storage, harnessing the power of FAISS and ElasticSearch. It boasts the capability to process diverse forms of input information, including textual video descriptions, Optical Character Recognition (OCR) results, Automatic Speech Recognition (ASR) transcriptions, visually similar images, and details about objects within videos, encompassing aspects such as color and quantity. Moreover, our system can also extract information about the temporal sequence of events within videos—a particularly challenging task when extracting information from video frames. By amalgamating these various input types, our system delivers optimal results.