85 citations · 273 across the 13 of their papers we have counts for
16 papers
NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime
Gengze Zhou, Yicong Hong, Jiazhao Zhang +9
Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, rais…
Lasting Effects of Abstract Pretraining Beyond Perplexity
Zachary Shinnick, Hemanth Saratchandran, Damien Teney +1
Language models are typically pretrained from random initialization. Recent work challenges this convention, showing that a brief warm-up on abstract, algorithmically generated dat…
Procedural Core: A Compact Recurrent Initialization for Vision Transformers
Zachary Shinnick, Christian Internò, Hemanth Saratchandran +2
Transformers are typically trained from random initialization, requiring all their capabilities to emerge from large-scale optimization. Recent work showed that a small amount of a…
Back from the Future: Key-Value Cache Management by Counter-Causal Surprise
Stephen Gould, Anton van den Hengel
Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years. Computational demands of large language…
MARec: Metadata Alignment for cold-start Recommendation
Julien Monteil, Volodymyr Vaskovych, Wentao Lu +2
For many recommender systems, the primary data source is a historical record of user clicks. The associated click matrix is often very sparse, as the number of users x products can…
Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation
Dong Gong, Wei Sun, Qinfeng Shi +2
Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs. The SR methods…
Deep Weakly-supervised Anomaly Detection
Guansong Pang, Chunhua Shen, Huidong Jin +1
Recent semi-supervised anomaly detection methods that are trained using small labeled anomaly examples and large unlabeled data (mostly normal data) have shown largely improved per…
MPTV: Matching Pursuit Based Total Variation Minimization for Image Deconvolution
Dong Gong, Mingkui Tan, Qinfeng Shi +2
Total variation (TV) regularization has proven effective for a range of computer vision tasks through its preferential weighting of sharp image edges. Existing TV-based methods, ho…
Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network
Lei Zhang, Peng Wang, Chunhua Shen +4
Deep neural networks have achieved remarkable success in single image super-resolution (SISR). The computing and memory requirements of these methods have hindered their applicatio…
Learning Deep Gradient Descent Optimization for Image Deconvolution
Dong Gong, Zhen Zhang, Qinfeng Shi +3
As an integral component of blind image deblurring, non-blind deconvolution removes image blur with a given blur kernel, which is essential but difficult due to the ill-posed natur…
FVQA: Fact-based Visual Question Answering
Peng Wang, Qi Wu, Chunhua Shen +2
Visual Question Answering (VQA) has attracted a lot of attention in both Computer Vision and Natural Language Processing communities, not least because it offers insight into the r…
Pushing the Limits of Deep CNNs for Pedestrian Detection
Qichang Hu, Peng Wang, Chunhua Shen +2
Compared to other applications in computer vision, convolutional neural networks have under-performed on pedestrian detection. A breakthrough was made very recently by using sophis…
Exploring Context with Deep Structured models for Semantic Segmentation
Guosheng Lin, Chunhua Shen, Anton van den Hengel +1
State-of-the-art semantic image segmentation methods are mostly based on training deep convolutional neural networks (CNNs). In this work, we proffer to improve semantic segmentati…
Efficient piecewise training of deep structured models for semantic segmentation
Guosheng Lin, Chunhua Shen, Anton van dan Hengel +1
Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation through…
Large-scale Binary Quadratic Optimization Using Semidefinite Relaxation and Applications
Peng Wang, Chunhua Shen, Anton van den Hengel +1
In computer vision, many problems such as image segmentation, pixel labelling, and scene parsing can be formulated as binary quadratic programs (BQPs). For submodular problems, cut…
Characterness: An Indicator of Text in the Wild
Yao Li, Wenjing Jia, Chunhua Shen +1
Text in an image provides vital information for interpreting its contents, and text in a scene can aide with a variety of tasks from navigation, to obstacle avoidance, and odometry…