Alert button
Picture for Dohwan Ko

Dohwan Ko

Alert button

Large Language Models are Temporal and Causal Reasoners for Video Question Answering

Nov 06, 2023
Dohwan Ko, Ji Soo Lee, Wooyoung Kang, Byungseok Roh, Hyunwoo J. Kim

Viaarxiv icon

Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models

Aug 18, 2023
Dohwan Ko, Ji Soo Lee, Miso Choi, Jaewon Chu, Jihwan Park, Hyunwoo J. Kim

Figure 1 for Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
Figure 2 for Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
Figure 3 for Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
Figure 4 for Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
Viaarxiv icon

MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models

Mar 23, 2023
Dohwan Ko, Joonmyung Choi, Hyeong Kyu Choi, Kyoung-Woon On, Byungseok Roh, Hyunwoo J. Kim

Figure 1 for MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
Figure 2 for MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
Figure 3 for MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
Figure 4 for MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
Viaarxiv icon

Video-Text Representation Learning via Differentiable Weak Temporal Alignment

Mar 31, 2022
Dohwan Ko, Joonmyung Choi, Juyeon Ko, Shinyeong Noh, Kyoung-Woon On, Eun-Sol Kim, Hyunwoo J. Kim

Figure 1 for Video-Text Representation Learning via Differentiable Weak Temporal Alignment
Figure 2 for Video-Text Representation Learning via Differentiable Weak Temporal Alignment
Figure 3 for Video-Text Representation Learning via Differentiable Weak Temporal Alignment
Figure 4 for Video-Text Representation Learning via Differentiable Weak Temporal Alignment
Viaarxiv icon