156 citations
- Amazon (United States)US12 papers
- Massachusetts Institute of TechnologyUS7 papers
- Carnegie Mellon UniversityUS6 papers
- Google (United States)US5 papers
- Johns Hopkins UniversityUS5 papers
- Meta (Israel)IL5 papers
- California Southern UniversityUS4 papers
- Microsoft Research (United Kingdom)GB4 papers
- Toyota Technological Institute at ChicagoUS4 papers
- University of California, Los AngelesUS4 papers
- University of Southern CaliforniaUS4 papers
- National Yang Ming Chiao Tung UniversityTW3 papers
7 papers · 2 filters
TextTubes for Detecting Curved Text in the Wild
Joël Seytre, Jon Wu, Alessandro Achille
We present a detector for curved text in natural images. We model scene text instances as tubes around their medial axes and introduce a parametrization-invariant loss function. We…
Fashion Outfit Complementary Item Retrieval
Yen-Liang Lin, Son Tran, Larry S. Davis
Complementary fashion item recommendation is critical for fashion outfit completion. Existing methods mainly focus on outfit compatibility prediction but not in a retrieval setting…
TracKlinic: Diagnosis of Challenge Factors in Visual Tracking
Heng Fan, Fan Yang, Peng Chu +2
Generic visual tracking is difficult due to many challenge factors (e.g., occlusion, blur, etc.). Each of these factors may cause serious problems for a tracking algorithm, and whe…
Balancing Specialization, Generalization, and Compression for Detection and Tracking
Dotan Kaufman, Koby Bibas, Eran Borenstein +2
We propose a method for specializing deep detectors and trackers to restricted settings. Our approach is designed with the following goals in mind: (a) Improving accuracy in restri…
Unifying Heterogeneous Classifiers with Distillation
Jayakorn Vongkulbhisal, Phongtharin Vinayavekhin, Marco Visentini-Scarzanella
In this paper, we study the problem of unifying knowledge from a set of classifiers with different architectures and target classes into a single classifier, given only a generic s…
Learning to Generate Synthetic Data via Compositing
Shashank Tripathi, Siddhartha Chandra, Amit Agrawal +3
We present a task-aware approach to synthetic data generation. Our framework employs a trainable synthesizer network that is optimized to produce meaningful training samples by ass…