Related papers: ZippyPoint: Fast Interest Point Detection, Descrip…

Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background. Many existing methods usually require fine-grained…

Quantization is a widely used technique to compress and accelerate deep neural networks. However, conventional quantization methods use the same bit-width for all (or most of) the layers, which often suffer significant accuracy degradation…

Lossy image compression is generally formulated as a joint rate-distortion optimization to learn encoder, quantizer, and decoder. However, the quantizer is non-differentiable, and discrete entropy estimation usually is required for rate…

Redescription mining is a data analysis technique that has found applications in diverse fields. The most used redescription mining approaches involve two phases: finding matching pairs among data attributes and extending the pairs. This…

With the surging popularity of edge computing, the need to efficiently perform neural network inference on battery-constrained IoT devices has greatly increased. While algorithmic developments enable neural networks to solve increasingly…

In recent years increasingly complex architectures for deep convolution networks (DCNs) have been proposed to boost the performance on image recognition tasks. However, the gains in performance have come at a cost of substantial increase in…

In this paper, we provide an extensive evaluation of the performance of local descriptors for tracking applications. Many different descriptors have been proposed in the literature for a wide range of application in computer vision such as…

Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices. However, designing aggressively low-bit (e.g., 2-bit) quantization schemes on…

Keypoint detection and description is fundamental yet important in many vision applications. Most existing methods use detect-then-describe or detect-and-describe strategy to learn local features without considering their context…

Deep learning networks have become the de-facto standard in Computer Vision for industry and research. However, recent developments in their cousin, Natural Language Processing (NLP), have shown that there are areas where parameter-less…

Understanding and extracting 3D information of objects from monocular 2D images is a fundamental problem in computer vision. In the task of 3D object pose estimation, recent data driven deep neural network based approaches suffer from…

Model quantization helps to reduce model size and latency of deep neural networks. Mixed precision quantization is favorable with customized hardwares supporting arithmetic operations at multiple bit-widths to achieve maximum efficiency. We…

In this paper, we realize automatic visual recognition and direction estimation of pointing. We introduce the first neural pointing understanding method based on two key contributions. The first is the introduction of a first-of-its-kind…

Camera relocalization relies on 3D models of the scene with a large memory footprint that is incompatible with the memory budget of several applications. One solution to reduce the scene memory size is map compression by removing certain 3D…

A number of real world problems in many domains (e.g. sociology, biology, political science and communication networks) can be modeled as dynamic networks with nodes representing entities of interest and edges representing interactions…

Fine-grained classification is challenging because categories can only be discriminated by subtle and local differences. Variances in the pose, scale or rotation usually make the problem more difficult. Most fine-grained classification…

Subjective image quality measures based on deep neural networks are very related to models of visual neuroscience. This connection benefits engineering but, more interestingly, the freedom to optimize deep networks in different ways, make…

In recent times, there has been a notable surge in multimodal approaches that decorates raw LiDAR point clouds with camera-derived features to improve object detection performance. However, we found that these methods still grapple with the…

We present PrecisionBatching, a quantized inference algorithm for speeding up neural network execution on traditional hardware platforms at low bitwidths without the need for retraining or recalibration. PrecisionBatching decomposes a…

Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images…