Computer Vision - Algorithms and Applications

By Richard Szeliski. 2011

4,877 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

On Buggy Resizing Libraries and Surprising Subtleties in FID Calculation (2021, background): “A central principle in image processing, signal processing, graphics, and vision [24, 25, 27, 53, 70] is to blur or “prefilter” before subsampling, as a means of removing highfrequency information (thus preventing its misrepresentation downstream).”
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models (2022, background): “Visual recognition has become ubiquitous in our society [60], with applications in geolocalization [51], action recognition [57], street number transcription [44], satellite remote sensing [22], medical imaging [62], self-driving cars [19], etc.”
Multiview Compressive Coding for 3D Reconstruction (2023, background): “This is framed by the task of 3D reconstruction: given an image, fully reconstruct the scene in 3D. 3D reconstruction is a longstanding problem in AI with applications in robotics and AR/VR. Structure from Motion [18, 60] lifts images to 3D by triangulation.”
K-Net: Towards Unified Image Segmentation (2021, background): “Despite the different definitions of a ‘meaningful group’, all segmentation tasks essentially assign each pixel to one of the predefined meaningful groups [48].”
Spatially Transformed Adversarial Examples (2018, background): “Spatial Transformation In computer vision and graphics literature, Two main aspects determine the appearance of a pictured object (Szeliski, 2010): (1) the lighting and material, which determine”
A self-organizing neural network architecture for learning human-object interactions (2017, neutral): “3) which has shown higher discriminative power than the extensively used Bag of Visual Features (BoF) [53, 54].”
Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision (2016, background): “1 Introduction Understanding the 3D world is at the heart of successful computer vision applications in robotics, rendering and modeling [19].”
Learning Generative Models with Visual Attention (2013, background): “the transformation parameters, we can equivalently redefine u = [a, b, 4x, 4y], where a = s sin(θ) − 1 and b = s cos(θ) (see [26] for details).”
TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval (2020, background): “Interestingly, the learned weights Conv1D st and Conv1D ed in Figure 5 are similar to the edge detectors in image processing [29].”
Image Segmentation Using Deep Learning: A Survey (2020, background): “It involves partitioning images (or video frames) into multiple segments or objects [1].”
Towards Practical Verification of Machine Learning: The Case of Computer Vision Systems (2017, background): “Similarly, for φ6, DF(I(〈i, j〉); c) = c + I(〈i, j〉), where c is the bias used to adjust the brightness of the input image [45].”
A Lite Distributed Semantic Communication System for Internet of Things (2020, background): “…there are usually three steps, i) the traditional communication receiver to recover the raw data [7], ii) the feature extractor to obtain and interpret the meanings of the raw data for the decision [8], and iii) the effects due to decisions according to the extracted features [9], [10].”
Consistent video depth estimation (2020, methodology): “Traditional reconstructionmethods [Szeliski 2010] combine sparse structure-from-motion with dense multi-view stereo—essentially matching patches along epipolar lines.”
The Interface Theory of Perception (2009, neutral): “This process of construction is stunningly complex, a fact that becomes strikingly obvious as soon as one tries to build a device, such as a robotic vision system, that enacts the construction (e.g., Szeliski, 2010).”
AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence (2019, positive): “solution). The clearest example of this trend is in computer vision. First we tried to hand-code computational vision systems in the early decades of AI research and found that they did not work well [182]. We then switched to a hybrid approach wherein we manually designed features (e.g. edge-, text”
Vision-Based Driver Assistance Systems: Survey, Taxonomy and Advances (2015, background): “These topics are covered in detail by computer vision textbooks and open-source software libraries [18][19] and here we summarize it according to the needs of typical vision applications.”
Capturing the human figure through a wall (2015, methodology): “Finally, to ensure that the resultant ﬁgure is smooth, we perform alpha blending [Szeliski 2010].”