ECCV 2018

AMC: AutoML for Model Compression and Acceleration on Mobile Devices

ECCV 2018 NervanaSystems/distiller

Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets.

MODEL COMPRESSION

PyramidBox: A Context-assisted Single Shot Face Detector

ECCV 2018 PaddlePaddle/models

This paper proposes a novel context-assisted single shot face detector, named \emph{PyramidBox} to handle the hard face detection problem.

FACE DETECTION

Receptive Field Block Net for Accurate and Fast Object Detection

ECCV 2018 ruinmessi/RFBNet

Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from high computational costs.

REAL-TIME OBJECT DETECTION

Distractor-aware Siamese Networks for Visual Object Tracking

ECCV 2018 foolwood/DaSiamRPN

During the off-line training phase, an effective sampling strategy is introduced to control this distribution and make the model focus on the semantic distractors.

VISUAL OBJECT TRACKING VISUAL TRACKING

Acquisition of Localization Confidence for Accurate Object Detection

ECCV 2018 vacancy/PreciseRoIPooling

The network acquires this confidence of localization, which improves the NMS procedure by preserving accurately localized bounding boxes.

#14 best model for Object Detection on COCO

OBJECT DETECTION

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

ECCV 2018 XingangPan/IBN-Net

IBN-Net carefully integrates Instance Normalization (IN) and Batch Normalization (BN) as building blocks, and can be wrapped into many advanced deep networks to improve their performances.

DOMAIN ADAPTATION

Temporal Relational Reasoning in Videos

ECCV 2018 metalbubble/TRN-pytorch

Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species.

ACTIVITY RECOGNITION COMMON SENSE REASONING HUMAN-OBJECT INTERACTION DETECTION RELATIONAL REASONING

Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors

ECCV 2018 nmslib/hnsw

This work addresses the problem of billion-scale nearest neighbor search.

Diverse Image-to-Image Translation via Disentangled Representations

ECCV 2018 HsinYingLee/DRIT

Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time.

DOMAIN ADAPTATION SYNTHETIC-TO-REAL TRANSLATION