Zobrazeno 1 - 10
of 595
pro vyhledávání: '"Bhanu, Bir"'
We propose Sym-Net, a novel framework for Few-Shot Segmentation (FSS) that addresses the critical issue of intra-class variation by jointly learning both query and support prototypes in a symmetrical manner. Unlike previous methods that generate quer
Externí odkaz:
http://arxiv.org/abs/2407.19306
Autor:
Liu, Hengyue, Bhanu, Bir
Scene Graph Generation (SGG) has achieved significant progress recently. However, most previous works rely heavily on fixed-size entity representations based on bounding box proposals, anchors, or learnable queries. As each representation's cardinali
Externí odkaz:
http://arxiv.org/abs/2309.03240
We present RECLIP (Resource-efficient CLIP), a simple method that minimizes computational resource footprint for CLIP (Contrastive Language Image Pretraining). Inspired by the notion of coarse-to-fine in computer vision, we leverage small images to l
Externí odkaz:
http://arxiv.org/abs/2304.06028
Self-supervised monocular depth estimation has seen significant progress in recent years, especially in outdoor environments. However, depth prediction results are not satisfying in indoor scenes where most of the existing data are captured with hand
Externí odkaz:
http://arxiv.org/abs/2207.08951
A high-resolution network exhibits remarkable capability in extracting multi-scale features for human pose estimation, but fails to capture long-range interactions between joints and has high computational complexity. To address these problems, we pr
Externí odkaz:
http://arxiv.org/abs/2204.10762
Gradient-based attention modeling has been used widely as a way to visualize and understand convolutional neural networks. However, exploiting these visual explanations during the training of generative adversarial networks (GANs) is an unexplored ar
Externí odkaz:
http://arxiv.org/abs/2108.07466
Most of the existing works in supervised spatio-temporal video super-resolution (STVSR) heavily rely on a large-scale external dataset consisting of paired low-resolution low-frame rate (LR-LFR)and high-resolution high-frame-rate (HR-HFR) videos. Des
Externí odkaz:
http://arxiv.org/abs/2108.02832
We consider the problem of estimating frame-level full human body meshes given a video of a person with natural motion dynamics. While much progress in this field has been in single image-based mesh estimation, there has been a recent uptick in effor
Externí odkaz:
http://arxiv.org/abs/2107.12847
Self-supervised depth estimation for indoor environments is more challenging than its outdoor counterpart in at least the following two aspects: (i) the depth range of indoor sequences varies a lot across different frames, making it difficult for the
Externí odkaz:
http://arxiv.org/abs/2107.12429
This paper presents a fully convolutional scene graph generation (FCSGG) model that detects objects and relations simultaneously. Most of the scene graph generation frameworks use a pre-trained two-stage object detector, like Faster R-CNN, and build
Externí odkaz:
http://arxiv.org/abs/2103.16083