output
20152024
most citedFeature relevance quantification in explainable AI: A causal problem

156 citations

Showing 2019 · cs.CVShow all

7 papers · 2 filters

cs.CV20192 cited

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…

cs.CV20192 cited

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…

cs.CV20198 cited

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…

cs.CV20192 cited

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…

cs.CV20193 cited

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…

cs.CV20196 cited

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…