Zobrazeno 1 - 10
of 1 146
pro vyhledávání: '"Heo, Jae"'
Temporal Action Detection (TAD) is fundamental yet challenging for real-world video applications. Leveraging the unique benefits of transformers, various DETR-based approaches have been adopted in TAD. However, it has recently been identified that th
Externí odkaz:
http://arxiv.org/abs/2408.16729
Temporal action detection (TAD) is challenging, yet fundamental for real-world video applications. Recently, DETR-based models for TAD have been prevailing thanks to their unique benefits. However, transformers demand a huge dataset, and unfortunatel
Externí odkaz:
http://arxiv.org/abs/2408.13152
Few-shot object counting has garnered significant attention for its practicality as it aims to count target objects in a query image based on given exemplars without the need for additional training. However, there is a shortcoming in the prevailing
Externí odkaz:
http://arxiv.org/abs/2408.09734
Temporal action detection (TAD) is challenging, yet fundamental for real-world video applications. Large temporal scale variation of actions is one of the most primary difficulties in TAD. Naturally, multi-scale features have potential in localizing
Externí odkaz:
http://arxiv.org/abs/2408.09354
The labor-intensive labeling for semantic segmentation has spurred the emergence of Unsupervised Semantic Segmentation. Recent studies utilize patch-wise contrastive learning based on features from image-level self-supervised pretrained models. Howev
Externí odkaz:
http://arxiv.org/abs/2407.12463
Class-Incremental Semantic Segmentation(CISS) aims to learn new classes without forgetting the old ones, using only the labels of the new classes. To achieve this, two popular strategies are employed: 1) pseudo-labeling and knowledge distillation to
Externí odkaz:
http://arxiv.org/abs/2407.11859
Autor:
Hyun, Sangeek, Heo, Jae-Pil
Most advances in 3D Generative Adversarial Networks (3D GANs) largely depend on ray casting-based volume rendering, which incurs demanding rendering costs. One promising alternative is rasterization-based 3D Gaussian Splatting (3D-GS), providing a mu
Externí odkaz:
http://arxiv.org/abs/2406.02968
StyleGAN has shown remarkable performance in unconditional image generation. However, its high computational cost poses a significant challenge for practical applications. Although recent efforts have been made to compress StyleGAN while preserving i
Externí odkaz:
http://arxiv.org/abs/2403.13548
Autor:
Lee, MinKyu, Heo, Jae-Pil
Recent deep-learning-based single image super-resolution (SISR) methods have shown impressive performance whereas typical methods train their networks by minimizing the pixel-wise distance with respect to a given high-resolution (HR) image. However,
Externí odkaz:
http://arxiv.org/abs/2312.17526
Zero-Shot Object Counting (ZSOC) aims to count referred instances of arbitrary classes in a query image without human-annotated exemplars. To deal with ZSOC, preceding studies proposed a two-stage pipeline: discovering exemplars and counting. However
Externí odkaz:
http://arxiv.org/abs/2312.16580