Brody Huval's research while affiliated with Stanford University and other places

Publications (5)

Article
Full-text available
Numerous groups have applied a variety of deep learning techniques to computer vision problems in highway perception scenarios. In this paper, we presented a number of empirical evaluations of recent deep learning advances. Computer vision, combined with deep learning, has the potential to bring about a relatively inexpensive, robust solution to au...
Article
We investigate the use of deep neural networks for the novel task of class generic object detection. We show that neural networks originally designed for image recognition can be trained to detect objects within images, regardless of their class, including objects for which no bounding box labels have been provided. In addition, we show that boundi...
Article
Scaling up deep learning algorithms has been shown to lead to increased performance in benchmark tasks and to enable discovery of complex high-level features. Recent efforts to train extremely large networks (with over 1 billion parameters) have relied on cloud-like computing infrastructure and thousands of CPU cores. In this paper, we present tech...
Conference Paper
Single-word vector space models have been very successful at learning lexical information. However, they cannot capture the compositional meaning of longer phrases, preventing them from a deeper understanding of language. We introduce a recursive neural network (RNN) model that learns compositional vector representations for phrases and sentences o...
Article
Full-text available
Recent advances in 3D sensing technologies make it possible to easily record color and depth images which together can improve object recognition. Most current methods rely on very well-designed features for this new 3D modality. We in-troduce a model based on a combination of convolutional and recursive neural networks (CNN and RNN) for learning f...

Citations

... As technology develops, we will have better resources (e.g., GPUs), but image-acquisition quality will improve as well. HCT is a ResNet-22 variant, a shallow architecture compared to ResNet-101/152 and recent architectural development [5,2,44]. For high resolution inputs, a deep network is a luxury. ...
... As a vital function of dynamic traffic perception, lane detection has gained increasing attention in recent years. Meanwhile, vision-based lane detection technology has seen significant progress, and deep neural networks, such as the mainstream technology for computer vision, have been widely utilized in lane detection [3][4][5][6][7][8][9][10]. However, the application scenarios of most deep learning (DL)-based lane detection are still limited to ideal weather conditions, e.g., clear daytime. ...
... In terms of a CNN-based CFD prediction approach, Guo et al. [17] proposed a CNN model for predicting stationary flow fields around solid objects. Moreover, previous studies [26,27] have used CNN models to learn arbitrary geometry representations. Georgiou et al. [28] developed a CNN application for reconstructing fluid force and flow prediction. ...
... Later, some scholars applied machine learning methods to medical text relation extraction and regarded the relation extraction task as a classification problem to recognize the relation between entities [5]. Recently, deep learning methods have been most widely applied in medical relation extraction, with recurrent neural networks (RNNs) [6], convolutional neural networks (CNNs) [7], and pre-trained language models being the mainstream neural networks currently used for relation extraction. ...
... The model uses five different training procedures to figure out the object locations in the frames. Similarly another DNN model was developed by Brody et al. which produces bounding boxes around the objects in the frames [11]. Though efficiency degradation due to poor fine-grained categorization is overcome by pose-normalization, these methods still require boundingbox hypotheses and hence zhang et al. proposed a bottom-up strategy in Deep CNN. ...