Large-scale video generative models have recently demonstrated strong visual capabilities, enabling the prediction of future frames that adhere to the logical and physical cues in the current observation. In this work, we investigate whether such capabilities can be harnessed for controllable image-to-video generation by interpreting visual signals embedded within the frames as instructions, a paradigm we term In-Video Instruction. In contrast to prompt-based control, which provides textual descriptions that are inherently global and coarse, In-Video Instruction encodes user guidance directly into the visual domain through elements such as overlaid text, arrows, or trajectories. This enables explicit, spatial-aware, and unambiguous correspondences between visual subjects and their intended actions by assigning distinct instructions to different objects. Extensive experiments on three state-of-the-art generators, including Veo 3.1, Kling 2.5, and Wan 2.2, show that video models can reliably interpret and execute such visually embedded instructions, particularly in complex multi-object scenarios.

Effective human-robot collaboration hinges on robust communication channels, with visual signaling playing a pivotal role due to its intuitive appeal. Yet, the creation of visually intuitive cues often demands extensive resources and specialized knowledge. The emergence of Large Language Models (LLMs) offers promising avenues for enhancing human-robot interactions and revolutionizing the way we generate context-aware visual cues. To this end, we introduce SiSCo--a novel framework that combines the computational power of LLMs with mixed-reality technologies to streamline the creation of visual cues for human-robot collaboration. Our results show that SiSCo improves the efficiency of communication in human-robot teaming tasks, reducing task completion time by approximately 73% and increasing task success rates by 18% compared to baseline natural language signals. Additionally, SiSCo reduces cognitive load for participants by 46%, as measured by the NASA-TLX subscale, and receives above-average user ratings for on-the-fly signals generated for unseen objects. To encourage further development and broader community engagement, we provide full access to SiSCo's implementation and related materials on our GitHub repository.

We present DenseAV, a novel dual encoder grounding architecture that learns high-resolution, semantically meaningful, and audio-visually aligned features solely through watching videos. We show that DenseAV can discover the ``meaning'' of words and the ``location'' of sounds without explicit localization supervision. Furthermore, it automatically discovers and distinguishes between these two types of associations without supervision. We show that DenseAV's localization abilities arise from a new multi-head feature aggregation operator that directly compares dense image and audio representations for contrastive learning. In contrast, many other systems that learn ``global'' audio and video representations cannot localize words and sound. Finally, we contribute two new datasets to improve the evaluation of AV representations through speech and sound prompted semantic segmentation. On these and other datasets we show DenseAV dramatically outperforms the prior art on speech and sound prompted semantic segmentation. DenseAV outperforms the previous state-of-the-art, ImageBind, on cross-modal retrieval using fewer than half of the parameters. Project Page: \href{https://aka.ms/denseav}{https://aka.ms/denseav}

Augmented and mixed-reality techniques harbor a great potential for improving human-robot collaboration. Visual signals and cues may be projected to a human partner in order to explicitly communicate robot intentions and goals. However, it is unclear what type of signals support such a process and whether signals can be combined without adding additional cognitive stress to the partner. This paper focuses on identifying the effective types of visual signals and quantify their impact through empirical evaluations. In particular, the study compares static and dynamic visual signals within a collaborative object sorting task and assesses their ability to shape human behavior. Furthermore, an information-theoretic analysis is performed to numerically quantify the degree of information transfer between visual signals and human behavior. The results of a human subject experiment show that there are significant advantages to combining multiple visual signals within a single task, i.e., increased task efficiency and reduced cognitive load.

Contrastive learning is a form of distance learning that aims to learn invariant features from two related representations. In this paper, we explore the bold hypothesis that an image and its caption can be simply regarded as two different views of the underlying mutual information, and train a model to learn a unified vision-language representation space that encodes both modalities at once in a modality-agnostic manner. We first identify difficulties in learning a generic one-tower model for vision-language pretraining (VLP), and propose OneR as a simple yet effective framework for our goal. We discover intriguing properties that distinguish OneR from the previous works that learn modality-specific representation spaces such as zero-shot object localization, text-guided visual reasoning and multi-modal retrieval, and present analyses to provide insights into this new form of multi-modal representation learning. Thorough evaluations demonstrate the potential of a unified modality-agnostic VLP framework.

Understanding and comprehending video content is crucial for many real-world applications such as search and recommendation systems. While recent progress of deep learning has boosted performance on various tasks using visual cues, deep cognition to reason intentions, motivation, or causality remains challenging. Existing datasets that aim to examine video reasoning capability focus on visual signals such as actions, objects, relations, or could be answered utilizing text bias. Observing this, we propose a novel task, along with a new dataset: Trope Understanding in Movies and Animations (TrUMAn), with 2423 videos associated with 132 tropes, intending to evaluate and develop learning systems beyond visual signals. Tropes are frequently used storytelling devices for creative works. By coping with the trope understanding task and enabling the deep cognition skills of machines, data mining applications and algorithms could be taken to the next level. To tackle the challenging TrUMAn dataset, we present a Trope Understanding and Storytelling (TrUSt) with a new Conceptual Storyteller module, which guides the video encoder by performing video storytelling on a latent space. Experimental results demonstrate that state-of-the-art learning systems on existing tasks reach only 12.01% of accuracy with raw input signals. Also, even in the oracle case with human-annotated descriptions, BERT contextual embedding achieves at most 28% of accuracy. Our proposed TrUSt boosts the model performance and reaches 13.94% performance. We also provide detailed analysis to pave the way for future research. TrUMAn is publicly available at:https://www.cmlab.csie.ntu.edu.tw/project/trope

During training, the squared L2 error between the clean spectrogram and the predicted spectrogram is used as a loss function to train the network. At inference time, our separation model can be applied to arbitrarily long segments of video and varying numbers of speakers. The latter is achieved by either directly training the model with multiple-input visual streams (one for speaker), or simply by feeding the visual features of the desired speaker to the visual stream. For full details about the architecture and training process, see our full paper.15

Causality knowledge is crucial for many artificial intelligence systems. Conventional textual-based causality knowledge acquisition methods typically require laborious and expensive human annotations. As a result, their scale is often limited. Moreover, as no context is provided during the annotation, the resulting causality knowledge records (e.g., ConceptNet) typically do not take the context into consideration. To explore a more scalable way of acquiring causality knowledge, in this paper, we jump out of the textual domain and investigate the possibility of learning contextual causality from the visual signal. Compared with pure text-based approaches, learning causality from the visual signal has the following advantages: (1) Causality knowledge belongs to the commonsense knowledge, which is rarely expressed in the text but rich in videos; (2) Most events in the video are naturally time-ordered, which provides a rich resource for us to mine causality knowledge from; (3) All the objects in the video can be used as context to study the contextual property of causal relations. In detail, we first propose a high-quality dataset Vis-Causal and then conduct experiments to demonstrate that with good language and visual representation models as well as enough training signals, it is possible to automatically discover meaningful causal knowledge from the videos. Further analysis also shows that the contextual property of causal relations indeed exists, taking which into consideration might be crucial if we want to use the causality knowledge in real applications, and the visual signal could serve as a good resource for learning such contextual causality.

Autonomous Vehicles (AV) will transform transportation, but also the interaction between vehicles and pedestrians. In the absence of a driver, it is not clear how an AV can communicate its intention to pedestrians. One option is to use visual signals. To advance their design, we conduct four human-participant experiments and evaluate six representative AV visual signals for visibility, intuitiveness, persuasiveness, and usability at pedestrian crossings. Based on the results, we distill twelve practical design recommendations for AV visual signals, with focus on signal pattern design and placement. Moreover, the paper advances the methodology for experimental evaluation of visual signals, including lab, closed-course, and public road tests using an autonomous vehicle. In addition, the paper also reports insights on pedestrian crosswalk behaviours and the impacts of pedestrian trust towards AVs on the behaviors. We hope that this work will constitute valuable input to the ongoing development of international standards for AV lamps, and thus help mature automated driving in general.

Abstract--The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical. To better enable the intelligent sensing at the front-end, instead of compressing and transmitting visual signals or the ultimately utilized toplayer deep learning features, we propose to compactly represent and convey the intermediate-layer deep learning features of high generalization capability, to facilitate the collaborating approach between front and cloud ends. This strategy enables a good balance among the computational load, transmission load and the generalization ability for cloud servers when deploying the deep neural networks for large scale cloud based visual analysis. Moreover, the presented strategy also makes the standardization of deep feature coding more feasible and promising, as a series of tasks can simultaneously benefit from the transmitted intermediate layers. We also present the results for evaluation of lossless deep feature compression with four benchmark data compression methods, which provides meaningful investigations and baselines for future research and standardization activities. ECENTLY, deep neural networks (DNNs) have demonstrated the state-of-the-art performance in various computer vision tasks, e.g., image classification [1], [2], [3], [4], image object detection [5], [6], visual tracking [7], visual retrieval [8]. In contrast to the handcrafted features such as Scale-Invariant Feature Transform (SIFT) [9], deep learning based approaches are able to learn representative features directly from the vast amounts of data. For image classification, which is the fundamental task of computer vision, the AlexNet model [1] has achieved 9% better classification accuracy than the previous handcrafted methods in the 2012 ImageNet competition [10], which provides a large scale training dataset with 1.2 million images and one thousand categories. Inspired by the fantastic progress of AlexNet, DNN models continue to be the undisputed leaders in the competition of ImageNet. In particular, both VGGNet [2] and GoogLeNet [11] announced promising performance in the ILSVRC 2014 classification challenge, which demonstrated that deeper and wider architectures can bring great benefits in learning better representations via large scale datasets. In 2016, He et al. also proposed residual blocks to enable very deep learning structure [3]. With the advances of network infrastructure, cloud-based applications are springing up in recent years. In particular, the front-end devices acquire information from users or the physical world, which are subsequently transmitted to the cloud end (i.e., data center) for further process and analyses. In particular, for visual analysis, the front-end devices deployed in the real world such as surveillance cameras and wearable devices acquire massive visual data which are transmitted to the cloud side for analyses, as shown in Figure 1.