IEEE conference on computer vision and pattern recognition

2000

Citations in the corpus

• Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking (2011, background): “Further research explored the use of particle filters (Eade and Drummond 2006b), features at multiple scales (Chekhlov et al. 2006, 2007), and edge-based features (Eade and Drummond 2006a; Klein and Murray 2008), as well as recovery from tracking failure (Williams et al. 2007).”
• WALKING WALKing walking: Action Recognition from Action Echoes (2017, background): “Currently, human 3D-skeleton positions can be accurately and easily extracted from a single depth image [Shotton et al., 2013], greatly accelerating the progress in action recognition.”
• Graph Cuts and Efficient N-D Image Segmentation (2006, methodology): “…interactivity (Rother et al., 2004) (grab-cuts), using superpixels (Li et al., 2004) (lazy snapping), integrating high-level contextual information (Kumar et al., 2005) (obj-cuts), multi-level and banded methods (Lombaert et al., 2005; Xu et al., 2003; Juan and Boykov, 2006), binary segmentation…”
• Recent trends in deep learning based personality detection (2019, methodology): “Popular image preprocessing techniques in this domain include facial landmark identification, Facial Action Coding System (FACS), which gives the AUs in the face, and the Viola Jones face detection algorithm (Viola and Jones 2004).”
• Hashing for Distributed Data (2015, methodology): “In this work, inspired by (Norouzi & Fleet, 2013), we restrict the codeword to be an additive combination of the columns of a dictionary matrix C ∈ Rd×r. Formally, let b(x) be the r-bit binary hashing code of x, then the corresponding assigned codeword is Cb(x).”
• Discovering physical concepts with neural networks (2018, background): “Here we explain the difficulty of a neural network to learn representations of cyclic parameters, which was alluded to in the context of the qubit example (Section E 3, see [90, 91] for a detailed discussion relevant to computer vision).”
• Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning (2019, methodology): “The concept of knowledge distillation is originally proposed by Hinton et al [Hinton et al., 2015] for model compression [Yu et al., 2017].”