Detecting and segmenting individual objects, regardless of their category, is crucial for many applications such as action detection or robotic interaction. While this problem has been well-studied under the classic formulation of spatio-temporal grouping, state-of-the-art approaches do not make use of learning-based methods. To bridge this gap, we propose a simple learning-based approach for spatiotemporal grouping. Our approach leverages motion cues from optical flow as a bottom-up signal for separating objects from each other. Motion cues are then combined with appearance cues that provide a generic objectness prior for capturing the full extent of objects. We show that our approach outperforms all prior work on the benchmark FBMS dataset. One potential worry with learning-based methods is that they might overfit to the particular type of objects that they have been trained on. To address this concern, we propose two new benchmarks for generic, moving object detection, and show that our model matches topdown methods on common categories, while significantly out-performing both top-down and bottom-up methods on never-before-seen categories.

For many years, multi-object tracking benchmarks have focused on a handful of categories. Motivated primarily by surveillance and self-driving applications, these datasets provide tracks for people, vehicles, and animals, ignoring the vast majority of objects in the world. By contrast, in the related field of object detection, the introduction of large-scale, diverse datasets (e.g., COCO) have fostered significant progress in developing highly robust solutions. To bridge this gap, we introduce a similarly diverse dataset for Tracking Any Object (TAO) 4. It consists of 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average. Importantly, we adopt a bottomup approach for discovering a large vocabulary of 833 categories, an order of magnitude more than prior tracking benchmarks. To this end, we ask annotators to label objects that move at any point in the video, and give names to them post factum. Our vocabulary is both significantly larger and qualitatively different from existing tracking datasets. To ensure scalability of annotation, we employ a federated approach that focuses manual effort on labeling tracks for those relevant objects in a video (e.g., those that move). We perform an extensive evaluation of state-ofthe-art trackers and make a number of important discoveries regarding large-vocabulary tracking in an open-world. In particular, we show that existing single-and multi-object trackers struggle when applied to this scenario in the wild, and that detection-based, multi-object trackers are in fact competitive with user-initialized ones. We hope that our dataset and analysis will boost further progress in the tracking community.

By design, average precision (AP) for object detection aims to treat all classes independently: AP is computed independently per category and averaged. On the one hand, this is desirable as it treats all classes, rare to frequent, equally. On the other hand, it ignores cross-category confidence calibration, a key property in real-world use cases. Unfortunately, we find that on imbalanced, largevocabulary datasets, the default implementation of AP is neither category independent, nor does it directly reward properly calibrated detectors. In fact, we show that the default implementation produces a gameable metric, where a simple, nonsensical re-ranking policy can improve AP by a large margin. To address these limitations, we introduce two complementary metrics. First, we present a simple fix to the default AP implementation, ensuring that it is truly independent across categories as originally intended. We benchmark recent advances in large-vocabulary detection and find that many reported gains do not translate to improvements under our new per-class independent evaluation, suggesting recent improvements may arise from difficult to interpret changes to cross-category rankings. Given the importance of reliably benchmarking cross-category rankings, we consider a pooled version of AP (AP Pool ) that rewards properly calibrated detectors by directly comparing crosscategory rankings. Finally, we revisit classical approaches for calibration and find that explicitly calibrating detectors improves state-of-the-art on AP Pool by 1.7 points.

While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniques used for video are largely based off those for static images, potentially underutilizing rich video information. In this work, we rethink both the underlying network architecture and the stochastic learning paradigm for temporal data. To do so, we draw inspiration from classic theory on linear dynamic systems for modeling time series. By extending such models to include nonlinear mappings, we derive a series of novel recurrent neural networks that sequentially make top-down predictions about the future and then correct those predictions with bottom-up observations. Predictive-corrective networks have a number of desirable properties: (1) they can adaptively focus computation on "surprising" frames where predictions require large corrections, (2) they simplify learning in that only "residual-like" corrective terms need to be learned over time and (3) they naturally decorrelate an input data stream in a hierarchical fashion, producing a more reliable signal for learning at each layer of a network. We provide an extensive analysis of our lightweight and interpretable framework, and demonstrate that our model is competitive with the two-stream network on three challenging datasets without the need for computationally expensive optical flow.Comment: Accepted to CVPR 2017. [v2]: Updated Multi-LSTM mAP on MultiTHUMOS (should be 29.7, was initially reported as 29.6). [Project URL]: http://www.achaldave.com/projects/predictive-corrective

No abstract