Contrastive learning has recently shown immense potential in unsupervised visual representation learning. Existing studies this track mainly focus on intra-image invariance The typically uses rich transformations to construct positive pairs and then maximizes agreement using a contrastive loss. merits of inter-image invariance, conversely, remain much less explored. One major obstacle exploit i...

We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call “percepts” using Gated-Recurrent-Unit Recurrent Networks (GRUs). Our method relies on percepts that are extracted from all levels of a deep convolutional network trained on the large ImageNet dataset. While high-level percepts contain highly discriminative information, they tend t...

Video analysis and understanding represents a major challenge for computer vision and machine learning research. While previous work has traditionally relied on hand-crafted and task-specific representations, there is a growing interest in designing general video representations that could help solve tasks in video understanding such as human action recognition, video retrieval or video caption...

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance tends to degrade with increasing the IoU thresholds. Two main factors are responsible for this: 1) overfitting during training, due to exponentially vanishing...