Minsu Cho
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Minsu Cho has a total of 88 co-authors. Here are the top co-authors by number of shared publications:
- Suha Kwak
POSTECH
11 shared publications - Deunsol Jung
Pohang University of Science and Technology (POSTECH) South Korea
5 shared publications - Dahyun Kang
Pohang University of Science and Technology (POSTECH)
4 shared publications - Chiheon Kim
KAIST KAIST AItrics
3 shared publications - Jinwoo Shin
KAIST
3 shared publications Jongmin Lee
Pohang University of Science and Technology (POSTECH) South Korea
3 shared publications
Latest Publications
- 4 October 2026
- Published by Springer Nature
- p. 486-504
Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale
- 4 October 2026
- Published by Springer Nature
- p. 486-504
Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale
- 13 September 2026
- Published by Springer Nature
- p. 192-209
PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-Based 3D Visual Grounding
- 13 September 2026
- Published by Springer Nature
- p. 192-209
PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-Based 3D Visual Grounding
- 10 September 2026
- Published by Springer Nature
- p. 1-20
WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation
- 10 September 2026
- Published by Springer Nature
- p. 1-20
WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation
- Open Access
PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding
3D Visual Grounding (3DVG) is a critical bridge from vision-language perception to robotics, requiring both language understanding and 3D scene reasoning. Traditional supervised models leverage explicit 3D geometry but exhibit limited generalization, owing to the scarcity of 3D vision-language datasets and the limited reasoning capabilities compared to modern vision-language models (VLMs). We propose PanoGrounder, a generalizable 3DVG framework that couples multi-modal panoramic representation with pretrained 2D VLMs for strong vision-language reasoning. Panoramic renderings, augmented with 3D semantic and geometric features, serve as an intermediate representation between 2D and 3D, and offer two major benefits: (i) they can be directly fed to VLMs with minimal adaptation and (ii) they retain long-range object-to-object relations thanks to their 360-degree field of view. We devise a three-stage pipeline that places a compact set of panoramic viewpoints considering the scene layout and geometry, grounds a text query on each panoramic rendering with a VLM, and fuses per-view predictions into a single 3D bounding box via lifting. Our approach achieves state-of-the-art results on ScanRefer and Nr3D, and demonstrates superior generalization to unseen 3D datasets and text rephrasings.
Open AccessPanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding
3D Visual Grounding (3DVG) is a critical bridge from vision-language perception to robotics, requiring both language understanding and 3D scene reasoning. Traditional supervised models leverage explicit 3D geometry but exhibit limited generalization, owing to the scarcity of 3D vision-language datasets and the limited reasoning capabilities compared to modern vision-language models (VLMs). We propose PanoGrounder, a generalizable 3DVG framework that couples multi-modal panoramic representation with pretrained 2D VLMs for strong vision-language reasoning. Panoramic renderings, augmented with 3D semantic and geometric features, serve as an intermediate representation between 2D and 3D, and offer two major benefits: (i) they can be directly fed to VLMs with minimal adaptation and (ii) they retain long-range object-to-object relations thanks to their 360-degree field of view. We devise a three-stage pipeline that places a compact set of panoramic viewpoints considering the scene layout and geometry, grounds a text query on each panoramic rendering with a VLM, and fuses per-view predictions into a single 3D bounding box via lifting. Our approach achieves state-of-the-art results on ScanRefer and Nr3D, and demonstrates superior generalization to unseen 3D datasets and text rephrasings.
- Open Access
Affogato: Learning Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale
Affordance grounding-localizing object regions based on natural language descriptions of interactions-is a critical challenge for enabling intelligent agents to understand and interact with their environments. However, this task remains challenging due to the need for fine-grained part-level localization, the ambiguity arising from multiple valid interaction regions, and the scarcity of large-scale datasets. In this work, we introduce Affogato, a large-scale benchmark comprising 150K instances, annotated with open-vocabulary text descriptions and corresponding 3D affordance heatmaps across a diverse set of objects and interactions. Building on this benchmark, we develop simple yet effective vision-language models that leverage pretrained part-aware vision backbones and a text-conditional heatmap decoder. Our models trained with the Affogato dataset achieve promising performance on the existing 2D and 3D benchmarks, and notably, exhibit effectiveness in open-vocabulary cross-domain generalization. The Affogato dataset is shared in public: https://huggingface.co/datasets/project-affogato/affogato
Open AccessAffogato: Learning Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale
Affordance grounding-localizing object regions based on natural language descriptions of interactions-is a critical challenge for enabling intelligent agents to understand and interact with their environments. However, this task remains challenging due to the need for fine-grained part-level localization, the ambiguity arising from multiple valid interaction regions, and the scarcity of large-scale datasets. In this work, we introduce Affogato, a large-scale benchmark comprising 150K instances, annotated with open-vocabulary text descriptions and corresponding 3D affordance heatmaps across a diverse set of objects and interactions. Building on this benchmark, we develop simple yet effective vision-language models that leverage pretrained part-aware vision backbones and a text-conditional heatmap decoder. Our models trained with the Affogato dataset achieve promising performance on the existing 2D and 3D benchmarks, and notably, exhibit effectiveness in open-vocabulary cross-domain generalization. The Affogato dataset is shared in public: https://huggingface.co/datasets/project-affogato/affogato
- Open Access
Locality-Aware Zero-Shot Human-Object Interaction Detection
Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen categories, showing impressive results on various zero-shot settings. However, existing methods struggle to adapt CLIP representations for human-object pairs, as CLIP tends to overlook fine-grained information necessary for distinguishing interactions. To address this issue, we devise, LAIN, a novel zero-shot HOI detection framework enhancing the locality and interaction awareness of CLIP representations. The locality awareness, which involves capturing fine-grained details and the spatial structure of individual objects, is achieved by aggregating the information and spatial priors of adjacent neighborhood patches. The interaction awareness, which involves identifying whether and how a human is interacting with an object, is achieved by capturing the interaction pattern between the human and the object. By infusing locality and interaction awareness into CLIP representation, LAIN captures detailed information about the human-object pairs. Our extensive experiments on existing benchmarks show that LAIN outperforms previous methods on various zero-shot settings, demonstrating the importance of locality and interaction awareness for effective zero-shot HOI detection.
Open AccessLocality-Aware Zero-Shot Human-Object Interaction Detection
Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen categories, showing impressive results on various zero-shot settings. However, existing methods struggle to adapt CLIP representations for human-object pairs, as CLIP tends to overlook fine-grained information necessary for distinguishing interactions. To address this issue, we devise, LAIN, a novel zero-shot HOI detection framework enhancing the locality and interaction awareness of CLIP representations. The locality awareness, which involves capturing fine-grained details and the spatial structure of individual objects, is achieved by aggregating the information and spatial priors of adjacent neighborhood patches. The interaction awareness, which involves identifying whether and how a human is interacting with an object, is achieved by capturing the interaction pattern between the human and the object. By infusing locality and interaction awareness into CLIP representation, LAIN captures detailed information about the human-object pairs. Our extensive experiments on existing benchmarks show that LAIN outperforms previous methods on various zero-shot settings, demonstrating the importance of locality and interaction awareness for effective zero-shot HOI detection.
- Open Access
Memory-Modular Classification: Learning to Generalize with Memory Replacement
We propose a novel memory-modular learner for image classification that separates knowledge memorization from reasoning. Our model enables effective generalization to new classes by simply replacing the memory contents, without the need for model retraining. Unlike traditional models that encode both world knowledge and task-specific skills into their weights during training, our model stores knowledge in the external memory of web-crawled image and text data. At inference time, the model dynamically selects relevant content from the memory based on the input image, allowing it to adapt to arbitrary classes by simply replacing the memory contents. The key differentiator that our learner meta-learns to perform classification tasks with noisy web data from unseen classes, resulting in robust performance across various classification scenarios. Experimental results demonstrate the promising performance and versatility of our approach in handling diverse classification tasks, including zero-shot/few-shot classification of unseen classes, fine-grained classification, and class-incremental classification.
Open AccessMemory-Modular Classification: Learning to Generalize with Memory Replacement
We propose a novel memory-modular learner for image classification that separates knowledge memorization from reasoning. Our model enables effective generalization to new classes by simply replacing the memory contents, without the need for model retraining. Unlike traditional models that encode both world knowledge and task-specific skills into their weights during training, our model stores knowledge in the external memory of web-crawled image and text data. At inference time, the model dynamically selects relevant content from the memory based on the input image, allowing it to adapt to arbitrary classes by simply replacing the memory contents. The key differentiator that our learner meta-learns to perform classification tasks with noisy web data from unseen classes, resulting in robust performance across various classification scenarios. Experimental results demonstrate the promising performance and versatility of our approach in handling diverse classification tasks, including zero-shot/few-shot classification of unseen classes, fine-grained classification, and class-incremental classification.
- 6 December 2024
- Published by Springer Nature
- p. 74-91
Online Temporal Action Localization with Memory-Augmented Transformer
- 6 December 2024
- Published by Springer Nature
- p. 74-91
Online Temporal Action Localization with Memory-Augmented Transformer
- Open Access
ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
Temporal action segmentation and long-term action anticipation are two popular vision tasks for the temporal analysis of actions in videos. Despite apparent relevance and potential complementarity, these two problems have been investigated as separate and distinct tasks. In this work, we tackle these two problems, action segmentation and action anticipation, jointly using a unified diffusion model dubbed ActFusion. The key idea to unification is to train the model to effectively handle both visible and invisible parts of the sequence in an integrated manner; the visible part is for temporal segmentation, and the invisible part is for future anticipation. To this end, we introduce a new anticipative masking strategy during training in which a late part of the video frames is masked as invisible, and learnable tokens replace these frames to learn to predict the invisible future. Experimental results demonstrate the bi-directional benefits between action segmentation and anticipation. ActFusion achieves the state-of-the-art performance across the standard benchmarks of 50 Salads, Breakfast, and GTEA, outperforming task-specific models in both of the two tasks with a single unified model through joint learning.
Open AccessActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
Temporal action segmentation and long-term action anticipation are two popular vision tasks for the temporal analysis of actions in videos. Despite apparent relevance and potential complementarity, these two problems have been investigated as separate and distinct tasks. In this work, we tackle these two problems, action segmentation and action anticipation, jointly using a unified diffusion model dubbed ActFusion. The key idea to unification is to train the model to effectively handle both visible and invisible parts of the sequence in an integrated manner; the visible part is for temporal segmentation, and the invisible part is for future anticipation. To this end, we introduce a new anticipative masking strategy during training in which a late part of the video frames is masked as invisible, and learnable tokens replace these frames to learn to predict the invisible future. Experimental results demonstrate the bi-directional benefits between action segmentation and anticipation. ActFusion achieves the state-of-the-art performance across the standard benchmarks of 50 Salads, Breakfast, and GTEA, outperforming task-specific models in both of the two tasks with a single unified model through joint learning.
- Open Access
MVFormer: Diversifying Feature Normalization and Token Mixing for Efficient Vision Transformers
Active research is currently underway to enhance the efficiency of vision transformers (ViTs). Most studies have focused solely on effective token mixers, overlooking the potential relationship with normalization. To boost diverse feature learning, we propose two components: a normalization module called multi-view normalization (MVN) and a token mixer called multi-view token mixer (MVTM). The MVN integrates three differently normalized features via batch, layer, and instance normalization using a learnable weighted sum. Each normalization method outputs a different distribution, generating distinct features. Thus, the MVN is expected to offer diverse pattern information to the token mixer, resulting in beneficial synergy. The MVTM is a convolution-based multiscale token mixer with local, intermediate, and global filters, and it incorporates stage specificity by configuring various receptive fields for the token mixer at each stage, efficiently capturing ranges of visual patterns. We propose a novel ViT model, multi-vision transformer (MVFormer), adopting the MVN and MVTM in the MetaFormer block, the generalized ViT scheme. Our MVFormer outperforms state-of-the-art convolution-based ViTs on image classification, object detection, and instance and semantic segmentation with the same or lower parameters and MACs. Particularly, MVFormer variants, MVFormer-T, S, and B achieve 83.4%, 84.3%, and 84.6% top-1 accuracy, respectively, on ImageNet-1K benchmark.
Open AccessMVFormer: Diversifying Feature Normalization and Token Mixing for Efficient Vision Transformers
Active research is currently underway to enhance the efficiency of vision transformers (ViTs). Most studies have focused solely on effective token mixers, overlooking the potential relationship with normalization. To boost diverse feature learning, we propose two components: a normalization module called multi-view normalization (MVN) and a token mixer called multi-view token mixer (MVTM). The MVN integrates three differently normalized features via batch, layer, and instance normalization using a learnable weighted sum. Each normalization method outputs a different distribution, generating distinct features. Thus, the MVN is expected to offer diverse pattern information to the token mixer, resulting in beneficial synergy. The MVTM is a convolution-based multiscale token mixer with local, intermediate, and global filters, and it incorporates stage specificity by configuring various receptive fields for the token mixer at each stage, efficiently capturing ranges of visual patterns. We propose a novel ViT model, multi-vision transformer (MVFormer), adopting the MVN and MVTM in the MetaFormer block, the generalized ViT scheme. Our MVFormer outperforms state-of-the-art convolution-based ViTs on image classification, object detection, and instance and semantic segmentation with the same or lower parameters and MACs. Particularly, MVFormer variants, MVFormer-T, S, and B achieve 83.4%, 84.3%, and 84.6% top-1 accuracy, respectively, on ImageNet-1K benchmark.