no code implementations • ICML 2020 • Zhixuan Lin, Yi-Fu Wu, Skand Peri, Bofeng Fu, Jindong Jiang, Sungjin Ahn
The G-SWM not only unifies the key properties of previous models in a principled framework but also achieves two crucial new abilities, multi-modal uncertainty and situated behavior.
1 code implementation • 8 Jun 2023 • Ligong Han, Song Wen, Qi Chen, Zhixing Zhang, Kunpeng Song, Mengwei Ren, Ruijiang Gao, Anastasis Stathopoulos, Xiaoxiao He, Yuxiao Chen, Di Liu, Qilong Zhangli, Jindong Jiang, Zhaoyang Xia, Akash Srivastava, Dimitris Metaxas
Null-text inversion (NTI) optimizes null embeddings to align the reconstruction and inversion trajectories with larger CFG scales, enabling real image editing with cross-attention control.
1 code implementation • NeurIPS 2023 • Jindong Jiang, Fei Deng, Gautam Singh, Sungjin Ahn
The recent success of transformer-based image generative models in object-centric learning highlights the importance of powerful image generators for handling complex scenes.
1 code implementation • NeurIPS 2020 • Jindong Jiang, Sungjin Ahn
In this paper, we propose Generative Neurosymbolic Machines, a generative model that combines the benefits of distributed and symbolic representations to support both structured representations of symbolic components and density-based generation.
no code implementations • 5 Oct 2020 • Zhixuan Lin, Yi-Fu Wu, Skand Peri, Bofeng Fu, Jindong Jiang, Sungjin Ahn
Third, a few key abilities for more faithful temporal imagination such as multimodal uncertainty and situation-awareness are missing.
4 code implementations • ICLR 2020 • Zhixuan Lin, Yi-Fu Wu, Skand Vishwanath Peri, Weihao Sun, Gautam Singh, Fei Deng, Jindong Jiang, Sungjin Ahn
Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability which is a main obstacle towards modeling real-world scenes.
2 code implementations • ICLR 2020 • Jindong Jiang, Sepehr Janghorbani, Gerard de Melo, Sungjin Ahn
Scalability in terms of object density in a scene is a primary challenge in unsupervised sequential object-oriented representation learning.
8 code implementations • 4 Jun 2018 • Jindong Jiang, Lunan Zheng, Fei Luo, Zhijun Zhang
Indoor semantic segmentation has always been a difficult task in computer vision.
Ranked #26 on Semantic Segmentation on SUN-RGBD (using extra training data)
no code implementations • 21 May 2017 • Jindong Jiang, Zhijun Zhang, Yongqian Huang, Lunan Zheng
To improve segmentation performance, a novel neural network architecture (termed DFCN-DCRF) is proposed, which combines an RGB-D fully convolutional neural network (DFCN) with a depth-sensitive fully-connected conditional random field (DCRF).