James Philbin

Learn More
In this paper, we present a large-scale object retrieval system. The user supplies a query object by selecting a region of a query image, and the system returns a ranked list of images that contain the same object, retrieved from a large corpus. We demonstrate the scalability and performance of our system on a dataset of over 1 million images crawled from(More)
Despite significant recent advances in the field of face recognition [10, 14, 15, 17], implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly(More)
The state of the art in visual object retrieval from large databases is achieved by systems that are inspired by text retrieval. A key component of these approaches is that local regions of images are characterized using high-dimensional descriptors which are then mapped to ldquovisual wordsrdquo selected from a discrete vocabulary.This paper explores(More)
Given a query image of an object, our objective is to retrieve all instances of that object in a large (1M+) image database. We adopt the bag-of-visual-words architecture which has proven successful in achieving high precision at low recall. Unfortunately, feature detection and quantization are noisy processes and this can result in variation in the(More)
Orbit was an optimizing compiler for T, a dialect of Scheme. Its aggressive use of CPS conversion, novel closure representations, and efficient code generation strategies made it the best compiler for a Scheme dialect at the time and for many years to come. The design of T and Orbit directly spawned six PhD theses and one Masters thesis, and influenced many(More)
This paper proposes two novel image similarity measures for fast indexing via locality sensitive hashing. The similarity measures are applied and evaluated in the context of near duplicate image detection. The proposed method uses a visual vocabulary of vector quantized local feature descriptors (SIFT) and for retrieval exploits enhanced min-Hash(More)
This paper proposes and compares two novel schemes for near duplicate image and video-shot detection. The first approach is based on global hierarchical colour histograms, using Locality Sensitive Hashing for fast retrieval. The second approach uses local feature descriptors (SIFT) and for retrieval exploits techniques used in the information retrieval(More)
This paper reports our research results that improve second level bu er cache performance. Several previous studies have shown that a good single level cache replacement algorithm such as LRU does not work well with second level bu er caches. Second level bu er caches have di erent access pattern from rst level bu er caches because Accesses to second level(More)
While models of fine-grained recognition have made great progress in recent years, little work has focused on a key ingredient of making recognition work: data. We use publicly available, noisy data sources to train generic models which vastly improve upon state-of-the-art on finegrained benchmarks. First, we present an active learning system using(More)
Automatic organization of large, unordered image collections is an extremely challenging problem with many potential applications. Often, what is required is that images taken in the same place, of the same thing, or of the same person be conceptually grouped together. This work focuses on grouping images containing the same object, despite significant(More)