Convolutional neural networks (CNNs) can model complicated non-linear relations between images. However, they are notoriously sensitive to small changes in the input. Most CNNs trained to describe image-to-image mappings generate temporally unstable results when applied to video sequences, leading to flickering artifacts and other inconsistencies over time. In order to use CNNs for video material, previous methods have relied on estimating dense frame-to-frame motion information (optical flow) in the training and/or the inference phase, or by exploring recurrent learning structures. We take a different approach to the problem, posing temporal stability as a regularization of the cost function. The regularization is formulated to account for different types of motion that can occur between frames, so that temporally stable CNNs can be trained without the need for video material or expensive motion estimation. The training can be performed as a fine-tuning operation, without architectural modifications of the CNN. Our evaluation shows that the training strategy leads to large improvements in temporal smoothness. Moreover, in situations where the quantity of training data is limited, the regularization can help in boosting the generalization performance to a much larger extent than what is possible with na\"ive augmentation strategies.
Automatic generation of video captions is a fundamental challenge in computer vision. Recent techniques typically employ a combination of Convolutional Neural Networks (CNNs) and Recursive Neural Networks (RNNs) for video captioning. These methods mainly focus on tailoring sequence learning through RNNs for better caption generation, whereas off-the-shelf visual features are borrowed from CNNs. We argue that careful designing of visual features for this task is equally important, and present a visual feature encoding technique to generate semantically rich captions using Gated Recurrent Units (GRUs). Our method embeds rich temporal dynamics in visual features by hierarchically applying Short Fourier Transform to CNN features of the whole video. It additionally derives high level semantics from an object detector to enrich the representation with spatial dynamics of the detected objects. The final representation is projected to a compact space and fed to a language model. By learning a relatively simple language model comprising two GRU layers, we establish new state-of-the-art on MSVD and MSR-VTT datasets for METEOR and ROUGE_L metrics.
In this paper, we propose to disentangle and interpret contextual effects that are encoded in a pre-trained deep neural network. We use our method to explain the gaming strategy of the alphaGo Zero model. Unlike previous studies that visualized image appearances corresponding to the network output or a neural activation only from a global perspective, our research aims to clarify how a certain input unit (dimension) collaborates with other units (dimensions) to constitute inference patterns of the neural network and thus contribute to the network output. The analysis of local contextual effects w.r.t. certain input units is of special values in real applications. Explaining the logic of the alphaGo Zero model is a typical application. In experiments, our method successfully disentangled the rationale of each move during the Go game.
Our goal is for a robot to execute a previously unseen task based on a single video demonstration of the task. The success of our approach relies on the principle of transferring knowledge from seen tasks to unseen ones with similar semantics. More importantly, we hypothesize that to successfully execute a complex task from a single video demonstration, it is necessary to explicitly incorporate compositionality to the model. To test our hypothesis, we propose Neural Task Graph (NTG) Networks, which use task graph as the intermediate representation to modularize the representations of both the video demonstration and the derived policy. We show this formulation achieves strong inter-task generalization on two complex tasks: Block Stacking in BulletPhysics and Object Collection in AI2-THOR. We further show that the same principle is applicable to real-world videos. We show that NTG can improve data efficiency of few-shot activity understanding in the Breakfast Dataset.
This paper presents a method of learning qualitatively interpretable models in object detection using popular two-stage region-based ConvNet detection systems (i.e., R-CNN). R-CNN consists of a region proposal network and a RoI (Region-of-Interest) prediction network.By interpretable models, we focus on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations. We utilize a top-down hierarchical and compositional grammar model embedded in a directed acyclic AND-OR Graph (AOG) to explore and unfold the space of latent part configurations of RoIs. We propose an AOGParsing operator to substitute the RoIPooling operator widely used in R-CNN, so the proposed method is applicable to many state-of-the-art ConvNet based detection systems. The AOGParsing operator aims to harness both the explainable rigor of top-down hierarchical and compositional grammar models and the discriminative power of bottom-up deep neural networks through end-to-end training. In detection, a bounding box is interpreted by the best parse tree derived from the AOG on-the-fly, which is treated as the extractive rationale generated for interpreting detection. In learning, we propose a folding-unfolding method to train the AOG and ConvNet end-to-end. In experiments, we build on top of the R-FCN and test the proposed method on the PASCAL VOC 2007 and 2012 datasets with performance comparable to state-of-the-art methods.