CVPR 2025 Workshop VisCon Submissions

Sequentially Acquiring Concept Knowledge to Guide Continual Learning
Shivanand Kundargi, Kowshik Thopalli, Tejas Gokhale
- Published: 07 May 2025, Last Modified: 30 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor
Ethan Lin, Linxi Zhao, Atharva Sehgal, Jennifer J. Sun
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
SGBD: Sharpness-Aware Mirror Gradient with BLIP-Based Denoising for Robust Multimodal Product Recommendation
Sarthak Srivastava, Kathy Wu
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
HyperVLM: Hyperbolic Space Guided Vision Language Modeling for Hierarchical Multi-Modal Understanding
Sarthak Srivastava, Kathy Wu
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning
Xindi Wu, Hee Seung Hwang, Polina Kirichenko, Olga Russakovsky
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Emergence and Evolution of Interpretable Concepts in Diffusion Models Through the Lens of Sparse Autoencoders
Berk Tinaz, Zalan Fabian, Mahdi Soltanolkotabi
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Alec Helbling, Tuna Han Salih Meral, Benjamin Hoover, Pinar Yanardag, Duen Horng Chau
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
ProtoDepth: Unsupervised Continual Depth Completion with Prototypes
Patrick Rim, Hyoungseob Park, Suchisrit Gangopadhyay, Ziyao Zeng, Younjoon Chung, Alex Wong
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
SSCA: SigLIP-2 Sonar Concept Alignment
Trevor Brokowski, Alexandre Sallinen, Mary-Anne Hartley
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Learning reusable concepts across different video understanding tasks
Simone Alberto Peirone, Francesca Pistilli, Antonio Alliegro, Tatiana Tommasi, Giuseppe Averta
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era
Dan Oneata, Desmond Elliott, Stella Frank
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Contrastive Mean-Shift Learning for Generalized Category Discovery
Sua Choi, Dahyun Kang, Minsu Cho
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Memory-Modular Classification: Novel-Class Generalization with Web-Crawled Memory
Dahyun Kang, Ahmet Iscen, Eunchan Jo, Sua Choi, Minsu Cho, Cordelia Schmid
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Can generative models generate novel objects the same as familiar objects?
Zhaokun Xue, Chang Ye, Gamaleldin Fathy Elsayed, Junfeng He
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Dictionary-based Framework for Interpretable and Consistent Object Parsing
Tiezheng Zhang, Qihang Yu, Alan Yuille, Ju He
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
On Achieving Perfect Multimodal Alignment
Abhi Kamboj, Minh N. Do
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
PartComposer: Composing Part-Level Concepts from Single-Image Examples
Junyu Liu, R. Kenny Jones, Daniel Ritchie
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
Junho Kim, Hyungjin Chung, Byung-Hoon Kim
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
GaussianVAE: Adaptive Learning Dynamics of 3D Gaussians for High-Fidelity Super-Resolution
Shuja Khalid, Mohamed Ibrahim, Yang Liu
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
Xavier Thomas, Deepti Ghadiyaram
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Quantifying Interpretability in CLIP Models with Concept Consistency
Avinash Madasu, Vasudev Lal, Phillip Howard
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Can Visual Encoder Learn to See Arrows?
Naoyuki Terashita, Yusuke Tozaki, HIDEAKI OMOTE, Kha Cong Nguyen, Ryosuke Nakamoto, Yuta Koreeda, Hiroaki Ozaki
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Learning Hierarchically using Formal Concepts
Deepika Vemuri, Sayanta Adhikari, Ankit Saha, Vineeth N. Balasubramanian
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Pruning Visual Concepts for Efficient and Interpretable Transfer Learning
Zichao Li, Zong Ke
- Published: 07 May 2025, Last Modified: 30 May 2025
- VisCon 2025 Poster
- Readers: Everyone
Physical Rule-Guided Convolutional Neural Network
kishor datta gupta, Marufa Kamal, Rakib Hossain Rifat, Mohd Ariful Haque, Roy George
- Published: 07 May 2025, Last Modified: 29 May 2025
- VisCon 2025 Poster
- Readers: Everyone