Search
Results
-
Regressor Basis Learning for anchored super-resolution
(2017)Proceedings of the 23rd International Conference on Pattern Recognition, ICPR 2016Conference Paper -
A Gaussian process latent variable model for BRDF inference
(2015)2015 IEEE International Conference on Computer Vision (ICCV)Conference Paper -
Neural Architecture Search as Sparse Supernet
(2021)Proceedings of the AAAI Conference on Artificial IntelligenceThis paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-Path and Multi-Path Search to automated Mixed-Path Search. In particular, we model the NAS problem as a sparse supernet using a new continuous architecture representation with a mixture of sparsity constraints. The sparse supernet enables us to automatically achieve sparsely-mixed paths upon a compact set of nodes. To optimize the proposed sparse ...Conference Paper -
Robust Multi-Person Tracking from Moving Platforms
(2008)Dagstuhl Seminar Proceedings ~ Logic and Probability for Scene InterpretationConference Paper -
Implicit Neural Representations for Image Compression
(2022)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2022Implicit Neural Representations (INRs) gained attention as a novel and effective representation for various data types. Recently, prior work applied INRs to image compressing. Such compression algorithms are promising candidates as a general purpose approach for any coordinate-based data modality. However, in order to live up to this promise current INR-based compression algorithms need to improve their rate-distortion performance by a ...Conference Paper -
TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation
(2022)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2022Traditional domain adaptive semantic segmentation addresses the task of adapting a model to a novel target domain under limited or no additional supervision. While tackling the input domain gap, the standard domain adaptation settings assume no domain change in the output space. In semantic prediction tasks, different datasets are often labeled according to different semantic taxonomies. In many real-world settings, the target domain task ...Conference Paper -
3D Compositional Zero-Shot Learning with DeCompositional Consensus
(2022)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2022Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be composable beyond the observed object classes. Towards this, we present 3D Compositional Zero-shot Learning as a problem of part generalization from seen to unseen object classes for semantic segmentation. We provide a structured study through benchmarking the task with the proposed Compositional-PartNet ...Conference Paper -
Event-Based Fusion for Motion Deblurring with Cross-modal Attention
(2022)Lecture Notes in Computer Science ~ Computer Vision - ECCV 2022Traditional frame-based cameras inevitably suffer from motion blur due to long exposure times. As a kind of bio-inspired camera, the event camera records the intensity changes in an asynchronous way with high temporal resolution, providing valid image degradation information within the exposure time. In this paper, we rethink the event-based image deblurring problem and unfold it into an end-to-end two-stage image restoration network. To ...Conference Paper -
Exploring Cross-Image Pixel Contrast for Semantic Segmentation
(2021)2021 IEEE/CVF International Conference on Computer Vision (ICCV)Current semantic segmentation methods focus only on mining “local” context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilated convolution, neural attention) or structure aware optimization criteria (e.g., IoU-like loss). However, they ignore “global” context of the training data, i.e., rich semantic relations between pixels across different images. Inspired by recent advance in ...Conference Paper -
Task Switching Network for Multi-task Learning
(2021)2021 IEEE/CVF International Conference on Computer Vision (ICCV)We introduce Task Switching Networks (TSNs), a task-conditioned architecture with a single unified encoder/decoder for efficient multi-task learning. Multiple tasks are performed by switching between them, performing one task at a time. TSNs have a constant number of parameters irrespective of the number of tasks. This scalable yet conceptually simple approach circumvents the overhead and intricacy of task-specific network components in ...Conference Paper