We present a new AI task -Embodied Question Answering (EmbodiedQA) -where an agent is spawned at a random location in a 3D environment and asked a question ('What color is the car?').In order to answer, the agent must first intelligently navigate to explore the environment, gather information through first-person (egocentric) vision, and then answer the question ('orange'). This challenging task requires a range of AI skills -active perception, language understanding, goal-driven navigation, commonsense reasoning, and grounding of language into actions. In this work, we develop the environments, end-to-end-trained reinforcement learning agents, and evaluation protocols for EmbodiedQA.

To help bridge the gap between internet vision-style problems and the goal of vision for embodied perception we instantiate a large-scale navigation task -Embodied Question Answering [1] in photo-realistic environments (Matterport 3D). We thoroughly study navigation policies that utilize 3D point clouds, RGB images, or their combination. Our analysis of these models reveals several key findings. We find that two seemingly naive navigation baselines, forward-only and random, are strong navigators and challenging to outperform, due to the specific choice of the evaluation setting presented by [1]. We find a novel lossweighting scheme we call Inflection Weighting to be important when training recurrent models for navigation with behavior cloning and are able to out perform the baselines with this technique. We find that point clouds provide a richer signal than RGB images for learning obstacle avoidance, motivating the use (and continued study) of 3D deep learning models for embodied navigation.

No abstract

We address the problem of grounding free-form textual phrases by using weak supervision from image-caption pairs. We propose a novel end-to-end model that uses caption-toimage retrieval as a "downstream" task to guide the process of phrase localization. Our method, as a first step, infers the latent correspondences between regions-of-interest (RoIs) and phrases in the caption and creates a discriminative image representation using these matched RoIs. In the subsequent step, this learned representation is aligned with the caption. Our key contribution lies in building this "captionconditioned" image encoding which tightly couples both the tasks and allows the weak supervision to effectively guide visual grounding. We provide extensive empirical and qualitative analysis to investigate the different components of our proposed model and compare it with competitive baselines. For phrase localization, we report improvements of 4.9% and 1.3% (absolute) over prior state-of-the-art on the VisualGenome and Flickr30k Entities datasets. We also report results that are at par with the state-of-the-art on the downstream caption-to-image retrieval task on COCO and Flickr30k datasets.Recent works [20,21] have shown evidence that operating under such a paradigm helps boost performance for imagecaption matching. Generally, these models consist of two stages: (1) a local matching module that infers the latent region-phrase correspondences to generate local matching information, and (2) a global matching module that uses this information to perform image-caption matching. This setup allows phrase grounding to act as an intermediate and a prerequisite task for image-caption matching. It is important to note that the primary objective of such works has been on image-caption matching and not phrase grounding.An artifact of training under such a paradigm is the amplification of correlations between selective regions and phrases."Young girl holding a kitten" by Gennadiy Kolodkin is licensed under CC BY-NC-ND 2.0.

No abstract

We present an approach for unsupervised training of CNNs in order to learn discriminative face representations. We mine supervised training data by noting that multiple faces in the same video frame must belong to different persons and the same face tracked across multiple frames must belong to the same person. We obtain millions of face pairs from hundreds of videos without using any manual supervision. Although faces extracted from videos have a lower spatial resolution than those which are available as part of standard supervised face datasets such as LFW and CASIA-WebFace, the former represent a much more realistic setting, e.g. in surveillance scenarios where most of the faces detected are very small. We train our CNNs with the relatively low resolution faces extracted from video frames collected, and achieve a higher verification accuracy on the benchmark LFW dataset cf. hand-crafted features such as LBPs, and even surpasses the performance of state-of-the-art deep networks such as VGG-Face, when they are made to work with low resolution input images.

No abstract

No abstract