180 citations · 324 across the 8 of their papers we have counts for
8 papers
Slot State Space Models
Jindong Jiang, Fei Deng, Gautam Singh +2
Recent State Space Models (SSMs) such as S4, S5, and Mamba have shown remarkable computational benefits in long-range temporal dependency modeling. However, in many sequence modeli…
Improving Tuning-Free Real Image Editing with Proximal Guidance
Ligong Han, Song Wen, Qi Chen +13
DDIM inversion has revealed the remarkable potential of real image editing within diffusion-based methods. However, the accuracy of DDIM reconstruction degrades as larger classifie…
Improving Generative Imagination in Object-Centric World Models
Zhixuan Lin, Yi-Fu Wu, Skand Peri +3
The remarkable recent advances in object-centric generative world models raise a few questions. First, while many of the recent achievements are indispensable for making a general…
Generative Neurosymbolic Machines
Jindong Jiang, Sungjin Ahn
Reconciling symbolic and distributed representations is a crucial challenge that can potentially resolve the limitations of current deep learning. Remarkable advances in this direc…
SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
Zhixuan Lin, Yi-Fu Wu, Skand Vishwanath Peri +5
The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervise…
SCALOR: Generative World Models with Scalable Object Representations
Jindong Jiang, Sepehr Janghorbani, Gerard de Melo +1
Scalability in terms of object density in a scene is a primary challenge in unsupervised sequential object-oriented representation learning. Most of the previous models have been s…
RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation
Jindong Jiang, Lunan Zheng, Fei Luo +1
Indoor semantic segmentation has always been a difficult task in computer vision. In this paper, we propose an RGB-D residual encoder-decoder architecture, named RedNet, for indoor…
Incorporating Depth into both CNN and CRF for Indoor Semantic Segmentation
Jindong Jiang, Zhijun Zhang, Yongqian Huang +1
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 de…