Understanding expressions that refer to the physical world is crucial for such human-assisting systems in the real world, as robots that must perform actions that are expected by users. In real-world reference resolution, a system must ground the verbal information that appears in user interactions to the visual information observed in egocentric views. To this end, we propose a multimodal reference resolution task and construct a Japanese Conversation dataset for Real-world Reference Resolution (J-CRe3). Our dataset contains egocentric video and dialogue audio of real-world conversations between two people acting as a master and an assistant robot at home. The dataset is annotated with crossmodal tags between phrases in the utterances and the object bounding boxes in the video frames. These tags include indirect reference relations, such as predicate-argument structures and bridging references as well as direct reference relations. We also constructed an experimental model and clarified the challenges in multimodal reference resolution tasks.
Situated conversations, which refer to visual information as visual question answering (VQA), often contain ambiguities caused by reliance on directive information. This problem is exacerbated because some languages, such as Japanese, often omit subjective or objective terms. Such ambiguities in questions are often clarified by the contexts in conversational situations, such as joint attention with a user or user gaze information. In this study, we propose the Gaze-grounded VQA dataset (GazeVQA) that clarifies ambiguous questions using gaze information by focusing on a clarification process complemented by gaze information. We also propose a method that utilizes gaze target estimation results to improve the accuracy of GazeVQA tasks. Our experimental results showed that the proposed method improved the performance in some cases of a VQA system on GazeVQA and identified some typical problems of GazeVQA tasks that need to be improved.
For training a video-based action recognition model that accepts multi-view video, annotating frame-level labels is tedious and difficult. However, it is relatively easy to annotate sequence-level labels. This kind of coarse annotations are called as weak labels. However, training a multi-view video-based action recognition model with weak labels for frame-level perception is challenging. In this paper, we propose a novel learning framework, where the weak labels are first used to train a multi-view video-based base model, which is subsequently used for downstream frame-level perception tasks. The base model is trained to obtain individual latent embeddings for each view in the multi-view input. For training the model using the weak labels, we propose a novel latent loss function. We also propose a model that uses the view-specific latent embeddings for downstream frame-level action recognition and detection tasks. The proposed framework is evaluated using the MM Office dataset by comparing several baseline algorithms. The results show that the proposed base model is effectively trained using weak labels and the latent embeddings help the downstream models improve accuracy.
Novel view synthesis has recently made significant progress with the advent of Neural Radiance Fields (NeRF). DietNeRF is an extension of NeRF that aims to achieve this task from only a few images by introducing a new loss function for unknown viewpoints with no input images. The loss function assumes that a pre-trained feature extractor should output the same feature even if input images are captured at different viewpoints since the images contain the same object. However, while that assumption is ideal, in reality, it is known that as viewpoints continuously change, also feature vectors continuously change. Thus, the assumption can harm training. To avoid this harmful training, we propose ManifoldNeRF, a method for supervising feature vectors at unknown viewpoints using interpolated features from neighboring known viewpoints. Since the method provides appropriate supervision for each unknown viewpoint by the interpolated features, the volume representation is learned better than DietNeRF. Experimental results show that the proposed method performs better than others in a complex scene. We also experimented with several subsets of viewpoints from a set of viewpoints and identified an effective set of viewpoints for real environments. This provided a basic policy of viewpoint patterns for real-world application. The code is available at https://github.com/haganelego/ManifoldNeRF_BMVC2023
Small Object Detection (SOD) is an important machine vision topic because (i) a variety of real-world applications require object detection for distant objects and (ii) SOD is a challenging task due to the noisy, blurred, and less-informative image appearances of small objects. This paper proposes a new SOD dataset consisting of 39,070 images including 137,121 bird instances, which is called the Small Object Detection for Spotting Birds (SOD4SB) dataset. The detail of the challenge with the SOD4SB dataset is introduced in this paper. In total, 223 participants joined this challenge. This paper briefly introduces the award-winning methods. The dataset, the baseline code, and the website for evaluation on the public testset are publicly available.
In this paper, we realize automatic visual recognition and direction estimation of pointing. We introduce the first neural pointing understanding method based on two key contributions. The first is the introduction of a first-of-its-kind large-scale dataset for pointing recognition and direction estimation, which we refer to as the DP Dataset. DP Dataset consists of more than 2 million frames of over 33 people pointing in various styles annotated for each frame with pointing timings and 3D directions. The second is DeePoint, a novel deep network model for joint recognition and 3D direction estimation of pointing. DeePoint is a Transformer-based network which fully leverages the spatio-temporal coordination of the body parts, not just the hands. Through extensive experiments, we demonstrate the accuracy and efficiency of DeePoint. We believe DP Dataset and DeePoint will serve as a sound foundation for visual human intention understanding.
Recently, large-scale Vision and Language (V\&L) pretraining has become the standard backbone of many multimedia systems. While it has shown remarkable performance even in unseen situations, it often performs in ways not intuitive to humans. Particularly, they usually do not consider the pronunciation of the input, which humans would utilize to understand language, especially when it comes to unknown words. Thus, this paper inserts phonetic prior into Contrastive Language-Image Pretraining (CLIP), one of the V\&L pretrained models, to make it consider the pronunciation similarity among its pronunciation inputs. To achieve this, we first propose a phoneme embedding that utilizes the phoneme relationships provided by the International Phonetic Alphabet (IPA) chart as a phonetic prior. Next, by distilling the frozen CLIP text encoder, we train a pronunciation encoder employing the IPA-based embedding. The proposed model named IPA-CLIP comprises this pronunciation encoder and the original CLIP encoders (image and text). Quantitative evaluation reveals that the phoneme distribution on the embedding space represents phonetic relationships more accurately when using the proposed phoneme embedding. Furthermore, in some multimodal retrieval tasks, we confirm that the proposed pronunciation encoder enhances the performance of the text encoder and that the pronunciation encoder handles nonsense words in a more phonetic manner than the text encoder. Finally, qualitative evaluation verifies the correlation between the pronunciation encoder and human perception regarding pronunciation similarity.
Such human-assisting systems as robots need to correctly understand the surrounding situation based on observations and output the required support actions for humans. Language is one of the important channels to communicate with humans, and the robots are required to have the ability to express their understanding and action planning results. In this study, we propose a new task of operative action captioning that estimates and verbalizes the actions to be taken by the system in a human-assisting domain. We constructed a system that outputs a verbal description of a possible operative action that changes the current state to the given target state. We collected a dataset consisting of two images as observations, which express the current state and the state changed by actions, and a caption that describes the actions that change the current state to the target state, by crowdsourcing in daily life situations. Then we constructed a system that estimates operative action by a caption. Since the operative action's caption is expected to contain some state-changing actions, we use scene-graph prediction as an auxiliary task because the events written in the scene graphs correspond to the state changes. Experimental results showed that our system successfully described the operative actions that should be conducted between the current and target states. The auxiliary tasks that predict the scene graphs improved the quality of the estimation results.
Multiple human tracking is a fundamental problem for scene understanding. Although both accuracy and speed are required in real-world applications, recent tracking methods based on deep learning have focused on accuracy and require substantial running time. This study aims to improve running speed by performing human detection at a certain frame interval because it accounts for most of the running time. The question is how to maintain accuracy while skipping human detection. In this paper, we propose a method that complements the detection results with optical flow, based on the fact that someone's appearance does not change much between adjacent frames. To maintain the tracking accuracy, we introduce robust interest point selection within human regions and a tracking termination metric calculated by the distribution of the interest points. On the MOT20 dataset in the MOTChallenge, the proposed SDOF-Tracker achieved the best performance in terms of the total running speed while maintaining the MOTA metric. Our code is available at https://anonymous.4open.science/r/sdof-tracker-75AE.
In this paper, we propose a Multiple Human Tracking method using multi-cues including Primitive Action Features (MHT-PAF). MHT-PAF can perform the accurate human tracking in dynamic aerial videos captured by a drone. PAF employs a global context, rich information by multi-label actions, and a middle level feature. The accurate human tracking result using PAF helps multi-frame-based action recognition. In the experiments, we verified the effectiveness of the proposed method using the Okutama-Action dataset. Our code is available online.