Knowledge-based visual question answering (VQA) involves answering questions that require external knowledge not present in the image. Existing methods first retrieve knowledge from external resources, then reason over the selected knowledge, the inp
ut image, and question for answer prediction. However, this two-step approach could lead to mismatches that potentially limit the VQA performance. For example, the retrieved knowledge might be noisy and irrelevant to the question, and the re-embedded knowledge features during reasoning might deviate from their original meanings in the knowledge base (KB). To address this challenge, we propose PICa, a simple yet effective method that Prompts GPT3 via the use of Image Captions, for knowledge-based VQA. Inspired by GPT-3s power in knowledge retrieval and question answering, instead of using structured KBs as in previous work, we treat GPT-3 as an implicit and unstructured KB that can jointly acquire and process relevant knowledge. Specifically, we first convert the image into captions (or tags) that GPT-3 can understand, then adapt GPT-3 to solve the VQA task in a few-shot manner by just providing a few in-context VQA examples. We further boost performance by carefully investigating: (i) what text formats best describe the image content, and (ii) how in-context examples can be better selected and used. PICa unlocks the first use of GPT-3 for multimodal tasks. By using only 16 examples, PICa surpasses the supervised state of the art by an absolute +8.6 points on the OK-VQA dataset. We also benchmark PICa on VQAv2, where PICa also shows a decent few-shot performance.
In this paper, we present a neat yet effective transformer-based framework for visual grounding, namely TransVG, to address the task of grounding a language query to the corresponding region onto an image. The state-of-the-art methods, including two-
stage or one-stage ones, rely on a complex module with manually-designed mechanisms to perform the query reasoning and multi-modal fusion. However, the involvement of certain mechanisms in fusion module design, such as query decomposition and image scene graph, makes the models easily overfit to datasets with specific scenarios, and limits the plenitudinous interaction between the visual-linguistic context. To avoid this caveat, we propose to establish the multi-modal correspondence by leveraging transformers, and empirically show that the complex fusion modules (eg, modular attention network, dynamic graph, and multi-modal tree) can be replaced by a simple stack of transformer encoder layers with higher performance. Moreover, we re-formulate the visual grounding as a direct coordinates regression problem and avoid making predictions out of a set of candidates (emph{i.e.}, region proposals or anchor boxes). Extensive experiments are conducted on five widely used datasets, and a series of state-of-the-art records are set by our TransVG. We build the benchmark of transformer-based visual grounding framework and make the code available at url{https://github.com/djiajunustc/TransVG}.
In this paper, we propose Text-Aware Pre-training (TAP) for Text-VQA and Text-Caption tasks. These two tasks aim at reading and understanding scene text in images for question answering and image caption generation, respectively. In contrast to the c
onventional vision-language pre-training that fails to capture scene text and its relationship with the visual and text modalities, TAP explicitly incorporates scene text (generated from OCR engines) in pre-training. With three pre-training tasks, including masked language modeling (MLM), image-text (contrastive) matching (ITM), and relative (spatial) position prediction (RPP), TAP effectively helps the model learn a better aligned representation among the three modalities: text word, visual object, and scene text. Due to this aligned representation learning, even pre-trained on the same downstream task dataset, TAP already boosts the absolute accuracy on the TextVQA dataset by +5.4%, compared with a non-TAP baseline. To further improve the performance, we build a large-scale dataset based on the Conceptual Caption dataset, named OCR-CC, which contains 1.4 million scene text-related image-text pairs. Pre-trained on this OCR-CC dataset, our approach outperforms the state of the art by large margins on multiple tasks, i.e., +8.3% accuracy on TextVQA, +8.6% accuracy on ST-VQA, and +10.2 CIDEr score on TextCaps.
Inspired by the human ability to infer emotions from body language, we propose an automated framework for body language based emotion recognition starting from regular RGB videos. In collaboration with psychologists, we further extend the framework f
or psychiatric symptom prediction. Because a specific application domain of the proposed framework may only supply a limited amount of data, the framework is designed to work on a small training set and possess a good transferability. The proposed system in the first stage generates sequences of body language predictions based on human poses estimated from input videos. In the second stage, the predicted sequences are fed into a temporal network for emotion interpretation and psychiatric symptom prediction. We first validate the accuracy and transferability of the proposed body language recognition method on several public action recognition datasets. We then evaluate the framework on a proposed URMC dataset, which consists of conversations between a standardized patient and a behavioral health professional, along with expert annotations of body language, emotions, and potential psychiatric symptoms. The proposed framework outperforms other methods on the URMC dataset.
We improve one-stage visual grounding by addressing current limitations on grounding long and complex queries. Existing one-stage methods encode the entire language query as a single sentence embedding vector, e.g., taking the embedding from BERT or
the hidden state from LSTM. This single vector representation is prone to overlooking the detailed descriptions in the query. To address this query modeling deficiency, we propose a recursive sub-query construction framework, which reasons between image and query for multiple rounds and reduces the referring ambiguity step by step. We show our new one-stage method obtains 5.0%, 4.5%, 7.5%, 12.8% absolute improvements over the state-of-the-art one-stage baseline on ReferItGame, RefCOCO, RefCOCO+, and RefCOCOg, respectively. In particular, superior performances on longer and more complex queries validates the effectiveness of our query modeling.
In this paper, we study Tracking by Language that localizes the target box sequence in a video based on a language query. We propose a framework called GTI that decomposes the problem into three sub-tasks: Grounding, Tracking, and Integration. The th
ree sub-task modules operate simultaneously and predict the box sequence frame-by-frame. Grounding predicts the referred region directly from the language query. Tracking localizes the target based on the history of the grounded regions in previous frames. Integration generates final predictions by synergistically combining grounding and tracking. With the integration task as the key, we explore how to indicate the quality of the grounded regions in each frame and achieve the desired mutually beneficial combination. To this end, we propose an RT-integration method that defines and predicts two scores to guide the integration: 1) R-score represents the Region correctness whether the grounding prediction accurately covers the target, and 2) T-score represents the Template quality whether the region provides informative visual cues to improve tracking in future frames. We present our real-time GTI implementation with the proposed RT-integration, and benchmark the framework on LaSOT and Lingual OTB99 with highly promising results. Moreover, we produce a disambiguated version of LaSOT queries to facilitate future tracking by language studies.
Human body part segmentation refers to the task of predicting the semantic segmentation mask for each body part. Fully supervised body part segmentation methods achieve good performances but require an enormous amount of effort to annotate part masks
for training. In contrast to high annotation costs needed for a limited number of part mask annotations, a large number of weak labels such as poses and full body masks already exist and contain relevant information. Motivated by the possibility of using existing weak labels, we propose the first weakly supervised body part segmentation framework. The core idea is first converting the sparse weak labels such as keypoints to the initial estimate of body part masks, and then iteratively refine the part mask predictions. We name the initial part masks estimated from poses the part priors. With sufficient extra weak labels, our weakly supervised framework achieves a comparable performance (62.0% mIoU) to the fully supervised method (63.6% mIoU) on the Pascal-Person-Part dataset. Furthermore, in the extended semi-supervised setting, the proposed framework outperforms the state-of-art methods. Moreover, we extend our proposed framework to other keypoint-supervised part segmentation tasks such as face parsing.
