JKJeesoo Kim

Jeesoo Kim

*This is an algorithmically generated author record based on publicly available information.

Jeesoo Kim has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • SAVE: Protagonist Diversification with Structure Agnostic Video Editing

    by Yeji Song, Wonsik Shin, Junsoo Lee, Jeesoo Kim, Nojun Kwak


  • Open Access

    SAVE: Protagonist Diversification with Structure Agnostic Video Editing

    by Yeji Song, Wonsik Shin, Junsoo Lee, Jeesoo Kim, Nojun Kwak

    Driven by the upsurge progress in text-to-image (T2I) generation models, text-to-video (T2V) generation has experienced a significant advance as well. Accordingly, tasks such as modifying the object or changing the style in a video have been possible. However, previous works usually work well on trivial and consistent shapes, and easily collapse on a difficult target that has a largely different body shape from the original one. In this paper, we spot the bias problem in the existing video editing method that restricts the range of choices for the new protagonist and attempt to address this issue using the conventional image-level personalization method. We adopt motion personalization that isolates the motion from a single source video and then modifies the protagonist accordingly. To deal with the natural discrepancy between image and video, we propose a motion word with an inflated textual embedding to properly represent the motion in a source video. We also regulate the motion word to attend to proper motion-related areas by introducing a novel pseudo optical flow, efficiently computed from the pre-calculated attention maps. Finally, we decouple the motion from the appearance of the source video with an additional pseudo word. Extensive experiments demonstrate the editing capability of our method, taking a step toward more diverse and extensive video editing.

  • Few-Shot Image Generation with Mixup-Based Distance Learning

    by Chaerin Kong, Jeesoo Kim, Donghoon Han, Nojun Kwak


  • Unwed Single Mother YouTubers’ Media Performativity and Identity

    by Jeesoo Kim, Kyungju Kim, Seil Oh

    연구 목적: 이 연구는 미혼모의 정체성이 레거시 미디어에서 정상가족 이데올로기가 재생산되는 프레임과는 달리 미혼모 당사자가 유튜브 채널을 통해 주체적인 미디어 수행성을 통해서 자기 정체성을 구성하는 사회문화적 함의를 심층적으로 분석하는 것이 목적이다. 연구 방법: 양육미혼모 유튜버의 유튜브, 브이로그 등의 콘텐츠 분석과 심층면접 분석을 통하여 자료를 수집하고 연구자들의 ‘삼각 측정’을 통하여 타당한 해석을 도출하였다. 연구 내용: 양육미혼모 유튜버의 ‘강한 엄마’와 ‘모성 책무성’의 공감적 서사와 같은 미디어 수행성의 주체적 담론 생산은 탈사회적, 비인격적 문맥의 타자반복의 수행성과 대조를 보인다. 결론 및 제언: 본 연구는 ‘양육미혼모’에 관한 논의를 유튜버의 미디어 수행성에 기반한 정체성 연구로 그 지평을 확장시켰다. 또한 미혼모에 대한 인식을 개선하고 정상가족 담론을 넘어서 미혼모 관련 사회복지 실천 및 정책을 제안하는데 기초자료로 활용될 것으로 기대한다.


  • Open Access

    Few-shot Image Generation with Mixup-based Distance Learning

    by Chaerin Kong, Jeesoo Kim, Donghoon Han, Nojun Kwak

    Producing diverse and realistic images with generative models such as GANs typically requires large scale training with vast amount of images. GANs trained with limited data can easily memorize few training samples and display undesirable properties like "stairlike" latent space where interpolation in the latent space yields discontinuous transitions in the output space. In this work, we consider a challenging task of pretraining-free few-shot image synthesis, and seek to train existing generative models with minimal overfitting and mode collapse. We propose mixup-based distance regularization on the feature space of both a generator and the counterpart discriminator that encourages the two players to reason not only about the scarce observed data points but the relative distances in the feature space they reside. Qualitative and quantitative evaluation on diverse datasets demonstrates that our method is generally applicable to existing models to enhance both fidelity and diversity under few-shot setting. Code is available.

  • Open Access

    Author Correction: Sclerostin inhibits Wnt signaling through tandem interaction with two LRP6 ectodomains

    by Jinuk Kim, Wonhee Han, Taeyong Park, Eun Jin Kim, Injin Bang, Hyun Sik Lee, Yejin Jeong, Kyeonghwan Roh, Jeesoo Kim, Jong-Seo Kim, et al.