• Understanding VQA for Negative Answers through Visual and Linguistic Inference

Seungjun Jung, Junyoung Byun, Kyujin Shim, and Changick Kim

• A Parameter Efficient Multi-Scale Capsule Network

Minki Jeong  and Changick Kim

• Weakly-Supervised Multiple Object Tracking via a Masked Center Point Warping Loss

Sungjoon Yoon, Kyujin Shim, K. Park, and Changick Kim

• Rethinking Training Schedules for Verifiably Robust Networks

Hyojun Go, Junyoung Byun, and Changick Kim

• Fine-Grained Multi-Class Object Counting

Hyojun Go, Junyoung Byun, Byeongjun Park, M. Choi, S. Yoo, and Changick Kim