Minkyu Choi

Minkyu Choi, Kuan Han, Xiaokai Wang et al.

The human visual system uses two parallel pathways for spatial processing and object recognition. In contrast, computer vision systems tend to use a single feedforward pathway, rendering them less robust, adaptive, or efficient than human vision. To bridge this gap, we developed a dual-stream vision model inspired by the human eyes and brain. At the input level, the model samples two complementary visual patterns to mimic how the human eyes use magnocellular and parvocellular retinal ganglion cells to separate retinal inputs to the brain. At the backend, the model processes the separate input patterns through two branches of convolutional neural networks (CNN) to mimic how the human brain uses the dorsal and ventral cortical pathways for parallel visual processing. The first branch (WhereCNN) samples a global view to learn spatial attention and control eye movements. The second branch (WhatCNN) samples a local view to represent the object around the fixation. Over time, the two branches interact recurrently to build a scene representation from moving fixations. We compared this model with the human brains processing the same movie and evaluated their functional alignment by linear transformation. The WhereCNN and WhatCNN branches were found to differentially match the dorsal and ventral pathways of the visual cortex, respectively, primarily due to their different learning objectives. These model-based results lead us to speculate that the distinct responses and representations of the ventral and dorsal streams are more influenced by their distinct goals in visual attention and object recognition than by their specific bias or selectivity in retinal inputs. This dual-stream model takes a further step in brain-inspired computer vision, enabling parallel neural networks to actively explore and understand the visual surroundings.

Minkyu Choi, Yizhen Zhang, Kuan Han et al.

Humans actively observe the visual surroundings by focusing on salient objects and ignoring trivial details. However, computer vision models based on convolutional neural networks (CNN) often analyze visual input all at once through a single feed-forward pass. In this study, we designed a dual-stream vision model inspired by the human brain. This model features retina-like input layers and includes two streams: one determining the next point of focus (the fixation), while the other interprets the visuals surrounding the fixation. Trained on image recognition, this model examines an image through a sequence of fixations, each time focusing on different parts, thereby progressively building a representation of the image. We evaluated this model against various benchmarks in terms of object recognition, gaze behavior and adversarial robustness. Our findings suggest that the model can attend and gaze in ways similar to humans without being explicitly trained to mimic human attention, and that the model can enhance robustness against adversarial attacks due to its retinal sampling and recurrent processing. In particular, the model can correct its perceptual errors by taking more glances, setting itself apart from all feed-forward-only models. In conclusion, the interactions of retinal sampling, eye movement, and recurrent dynamics are important to human-like visual exploration and inference.

Siyi Chen, Minkyu Choi, Zesen Zhao et al.

Taking inspiration from physical motion, we present a new self-supervised dynamics learning strategy for videos: Video Time-Differentiation for Instance Discrimination (ViDiDi). ViDiDi is a simple and data-efficient strategy, readily applicable to existing self-supervised video representation learning frameworks based on instance discrimination. At its core, ViDiDi observes different aspects of a video through various orders of temporal derivatives of its frame sequence. These derivatives, along with the original frames, support the Taylor series expansion of the underlying continuous dynamics at discrete times, where higher-order derivatives emphasize higher-order motion features. ViDiDi learns a single neural network that encodes a video and its temporal derivatives into consistent embeddings following a balanced alternating learning algorithm. By learning consistent representations for original frames and derivatives, the encoder is steered to emphasize motion features over static backgrounds and uncover the hidden dynamics in original frames. Hence, video representations are better separated by dynamic features. We integrate ViDiDi into existing instance discrimination frameworks (VICReg, BYOL, and SimCLR) for pretraining on UCF101 or Kinetics and test on standard benchmarks including video retrieval, action recognition, and action detection. The performances are enhanced by a significant margin without the need for large models or extensive datasets.

Mohammad Omama, Po-han Li, Harsh Goel et al.

Mapping is crucial in robotics for localization and downstream decision-making. As robots are deployed in ever-broader settings, the maps they rely on continue to increase in size. However, storing these maps indefinitely (cold storage), transferring them across networks, or sending localization queries to cloud-hosted maps imposes prohibitive memory and bandwidth costs. We propose a text-enhanced compression framework that reduces both memory and bandwidth footprints while retaining high-fidelity localization. The key idea is to treat text as an alternative modality: one that can be losslessly compressed with large language models. We propose leveraging lightweight text descriptions combined with very small image feature vectors, which capture "complementary information" as a compact representation for the mapping task. Building on this, our novel technique, Similarity Space Replication (SSR), learns an adaptive image embedding in one shot that captures only the information "complementary" to the text descriptions. We validate our compression framework on multiple downstream localization tasks, including Visual Place Recognition as well as object-centric Monte Carlo localization in both indoor and outdoor settings. SSR achieves 2 times better compression than competing baselines on state-of-the-art datasets, including TokyoVal, Pittsburgh30k, Replica, and KITTI.

Minkyu Choi, S P Sharan, Harsh Goel et al.

Current text-to-video (T2V) generation models are increasingly popular due to their ability to produce coherent videos from textual prompts. However, these models often struggle to generate semantically and temporally consistent videos when dealing with longer, more complex prompts involving multiple objects or sequential events. Additionally, the high computational costs associated with training or fine-tuning make direct improvements impractical. To overcome these limitations, we introduce NeuS-E, a novel zero-training video refinement pipeline that leverages neuro-symbolic feedback to automatically enhance video generation, achieving superior alignment with the prompts. Our approach first derives the neuro-symbolic feedback by analyzing a formal video representation and pinpoints semantically inconsistent events, objects, and their corresponding frames. This feedback then guides targeted edits to the original video. Extensive empirical evaluations on both open-source and proprietary T2V models demonstrate that NeuS-E significantly enhances temporal and logical alignment across diverse prompts by almost 40%

Sahil Shah, S P Sharan, Harsh Goel et al.

While vision-language models (VLMs) excel at tasks involving single images or short videos, they still struggle with Long Video Question Answering (LVQA) due to its demand for complex multi-step temporal reasoning. Vanilla approaches, which simply sample frames uniformly and feed them to a VLM along with the question, incur significant token overhead. This forces aggressive downsampling of long videos, causing models to miss fine-grained visual structure, subtle event transitions, and key temporal cues. Recent works attempt to overcome these limitations through heuristic approaches; however, they lack explicit mechanisms for encoding temporal relationships and fail to provide any formal guarantees that the sampled context actually encodes the compositional or causal logic required by the question. To address these foundational gaps, we introduce NeuS-QA, a training-free, plug-and-play neuro-symbolic pipeline for LVQA. NeuS-QA first translates a natural language question into a logic specification that models the temporal relationship between frame-level events. Next, we construct a video automaton to model the video's frame-by-frame event progression, and finally employ model checking to compare the automaton against the specification to identify all video segments that satisfy the question's logical requirements. Only these logic-verified segments are submitted to the VLM, thus improving interpretability, reducing hallucinations, and enabling compositional reasoning without modifying or fine-tuning the model. Experiments on the LongVideoBench and CinePile LVQA benchmarks show that NeuS-QA significantly improves performance by over 10%, particularly on questions involving event ordering, causality, and multi-step reasoning. We open-source our code at https://utaustin-swarmlab.github.io/NeuS-QA/.

Minkyu Choi, Harsh Goel, Mohammad Omama et al.

The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks. Long-term temporal reasoning is a key desideratum for frame retrieval systems. While state-of-the-art foundation models, like VideoLLaMA and ViCLIP, are proficient in short-term semantic understanding, they surprisingly fail at long-term reasoning across frames. A key reason for this failure is that they intertwine per-frame perception and temporal reasoning into a single deep network. Hence, decoupling but co-designing semantic understanding and temporal reasoning is essential for efficient scene identification. We propose a system that leverages vision-language models for semantic understanding of individual frames but effectively reasons about the long-term evolution of events using state machines and temporal logic (TL) formulae that inherently capture memory. Our TL-based reasoning improves the F1 score of complex event identification by 9-15% compared to benchmarks that use GPT4 for reasoning on state-of-the-art self-driving datasets such as Waymo and NuScenes.

Jonathan Salfity, Selma Wanna, Minkyu Choi et al.

Recent works in Task and Motion Planning (TAMP) show that training control policies on language-supervised robot trajectories with quality labeled data markedly improves agent task success rates. However, the scarcity of such data presents a significant hurdle to extending these methods to general use cases. To address this concern, we present an automated framework to decompose trajectory data into temporally bounded and natural language-based descriptive sub-tasks by leveraging recent prompting strategies for Foundation Models (FMs) including both Large Language Models (LLMs) and Vision Language Models (VLMs). Our framework provides both time-based and language-based descriptions for lower-level sub-tasks that comprise full trajectories. To rigorously evaluate the quality of our automatic labeling framework, we contribute an algorithm SIMILARITY to produce two novel metrics, temporal similarity and semantic similarity. The metrics measure the temporal alignment and semantic fidelity of language descriptions between two sub-task decompositions, namely an FM sub-task decomposition prediction and a ground-truth sub-task decomposition. We present scores for temporal similarity and semantic similarity above 90%, compared to 30% of a randomized baseline, for multiple robotic environments, demonstrating the effectiveness of our proposed framework. Our results enable building diverse, large-scale, language-supervised datasets for improved robotic TAMP.

Sahil Shah, Harsh Goel, Sai Shankar Narasimhan et al.

Modern video understanding systems excel at tasks such as scene classification, object detection, and short video retrieval. However, as video analysis becomes increasingly central to real-world applications, there is a growing need for proactive video agents for the systems that not only interpret video streams but also reason about events and take informed actions. A key obstacle in this direction is temporal reasoning: while deep learning models have made remarkable progress in recognizing patterns within individual frames or short clips, they struggle to understand the sequencing and dependencies of events over time, which is critical for action-driven decision-making. Addressing this limitation demands moving beyond conventional deep learning approaches. We posit that tackling this challenge requires a neuro-symbolic perspective, where video queries are decomposed into atomic events, structured into coherent sequences, and validated against temporal constraints. Such an approach can enhance interpretability, enable structured reasoning, and provide stronger guarantees on system behavior, all key properties for advancing trustworthy video agents. To this end, we present a grand challenge to the research community: developing the next generation of intelligent video agents that integrate three core capabilities: (1) autonomous video search and analysis, (2) seamless real-world interaction, and (3) advanced content generation. By addressing these pillars, we can transition from passive perception to intelligent video agents that reason, predict, and act, pushing the boundaries of video understanding.

Minkyu Choi, Yunhao Yang, Neel P. Bhatt et al.

Many robots (e.g., iRobot's Roomba) operate based on visual observations from live video streams, and such observations may inadvertently include privacy-sensitive objects, such as personal identifiers. Existing approaches for preserving privacy rely on deep learning models, differential privacy, or cryptography. They lack guarantees for the complete concealment of all sensitive objects. Guaranteeing concealment requires post-processing techniques and thus is inadequate for real-time video streams. We develop a method for privacy-constrained video streaming, PCVS, that conceals sensitive objects within real-time video streams. PCVS takes a logical specification constraining the existence of privacy-sensitive objects, e.g., never show faces when a person exists. It uses a detection model to evaluate the existence of these objects in each incoming frame. Then, it blurs out a subset of objects such that the existence of the remaining objects satisfies the specification. We then propose a conformal prediction approach to (i) establish a theoretical lower bound on the probability of the existence of these objects in a sequence of frames satisfying the specification and (ii) update the bound with the arrival of each subsequent frame. Quantitative evaluations show that PCVS achieves over 95 percent specification satisfaction rate in multiple datasets, significantly outperforming other methods. The satisfaction rate is consistently above the theoretical bounds across all datasets, indicating that the established bounds hold. Additionally, we deploy PCVS on robots in real-time operation and show that the robots operate normally without being compromised when PCVS conceals objects.

Mustafa Munir, Harsh Goel, Xiwen Wei et al.

Video editing and synthesis often introduce object inconsistencies, such as frame flicker and identity drift that degrade perceptual quality. To address these issues, we introduce ObjectAlign, a novel framework that seamlessly blends perceptual metrics with symbolic reasoning to detect, verify, and correct object-level and temporal inconsistencies in edited video sequences. The novel contributions of ObjectAlign are as follows: First, we propose learnable thresholds for metrics characterizing object consistency (i.e. CLIP-based semantic similarity, LPIPS perceptual distance, histogram correlation, and SAM-derived object-mask IoU). Second, we introduce a neuro-symbolic verifier that combines two components: (a) a formal, SMT-based check that operates on masked object embeddings to provably guarantee that object identity does not drift, and (b) a temporal fidelity check that uses a probabilistic model checker to verify the video's formal representation against a temporal logic specification. A frame transition is subsequently deemed "consistent" based on a single logical assertion that requires satisfying both the learned metric thresholds and this unified neuro-symbolic constraint, ensuring both low-level stability and high-level temporal correctness. Finally, for each contiguous block of flagged frames, we propose a neural network based interpolation for adaptive frame repair, dynamically choosing the interpolation depth based on the number of frames to be corrected. This enables reconstruction of the corrupted frames from the last valid and next valid keyframes. Our results show up to 1.4 point improvement in CLIP Score and up to 6.1 point improvement in warp error compared to SOTA baselines on the DAVIS and Pexels video datasets.

Yizhen Zhang, Minkyu Choi, Kuan Han et al.

In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast, humans learn language by grounding concepts in perception and action and the brain encodes grounded semantics for cognition. Inspired by this notion and recent work in vision-language learning, we design a two-stream model for grounding language learning in vision. The model includes a VGG-based visual stream and a Bert-based language stream. The two streams merge into a joint representational space. Through cross-modal contrastive learning, the model first learns to align visual and language representations with the MS COCO dataset. The model further learns to retrieve visual objects with language queries through a cross-modal attention module and to infer the visual relations between the retrieved objects through a bilinear operator with the Visual Genome dataset. After training, the language stream of this model is a stand-alone language model capable of embedding concepts in a visually grounded semantic space. This semantic space manifests principal dimensions explainable with human intuition and neurobiological knowledge. Word embeddings in this semantic space are predictive of human-defined norms of semantic features and are segregated into perceptually distinctive clusters. Furthermore, the visually grounded language model also enables compositional language understanding based on visual knowledge and multimodal image search with queries based on images, texts, or their combinations.

Minkyu Choi, Takazumi Matsumoto, Minju Jung et al.

The current paper presents how a predictive coding type deep recurrent neural networks can generate vision-based goal-directed plans based on prior learning experience by examining experiment results using a real arm robot. The proposed deep recurrent neural network learns to predict visuo-proprioceptive sequences by extracting an adequate predictive model from various visuomotor experiences related to object-directed behaviors. The predictive model was developed in terms of mapping from intention state space to expected visuo-proprioceptive sequences space through iterative learning. Our arm robot experiments adopted with three different tasks with different levels of difficulty showed that the error minimization principle in the predictive coding framework applied to inference of the optimal intention states for given goal states can generate goal-directed plans even for unlearned goal states with generalization. It was, however, shown that sufficient generalization requires relatively large number of learning trajectories. The paper discusses possible countermeasure to overcome this problem.

Minkyu Choi, Jun Tani

The current paper proposes a novel predictive coding type neural network model, the predictive multiple spatio-temporal scales recurrent neural network (P-MSTRNN). The P-MSTRNN learns to predict visually perceived human whole-body cyclic movement patterns by exploiting multiscale spatio-temporal constraints imposed on network dynamics by using differently sized receptive fields as well as different time constant values for each layer. After learning, the network becomes able to proactively imitate target movement patterns by inferring or recognizing corresponding intentions by means of the regression of prediction error. Results show that the network can develop a functional hierarchy by developing a different type of dynamic structure at each layer. The paper examines how model performance during pattern generation as well as predictive imitation varies depending on the stage of learning. The number of limit cycle attractors corresponding to target movement patterns increases as learning proceeds. And, transient dynamics developing early in the learning process successfully perform pattern generation and predictive imitation tasks. The paper concludes that exploitation of transient dynamics facilitates successful task performance during early learning periods.

Jungsik Hwang, Jinhyung Kim, Ahmadreza Ahmadi et al.

This study presents a dynamic neural network model based on the predictive coding framework for perceiving and predicting the dynamic visuo-proprioceptive patterns. In our previous study [1], we have shown that the deep dynamic neural network model was able to coordinate visual perception and action generation in a seamless manner. In the current study, we extended the previous model under the predictive coding framework to endow the model with a capability of perceiving and predicting dynamic visuo-proprioceptive patterns as well as a capability of inferring intention behind the perceived visuomotor information through minimizing prediction error. A set of synthetic experiments were conducted in which a robot learned to imitate the gestures of another robot in a simulation environment. The experimental results showed that with given intention states, the model was able to mentally simulate the possible incoming dynamic visuo-proprioceptive patterns in a top-down process without the inputs from the external environment. Moreover, the results highlighted the role of minimizing prediction error in inferring underlying intention of the perceived visuo-proprioceptive patterns, supporting the predictive coding account of the mirror neuron systems. The results also revealed that minimizing prediction error in one modality induced the recall of the corresponding representation of another modality acquired during the consolidative learning of raw-level visuo-proprioceptive patterns.

Minkyu Choi, Jun Tani

The current paper presents a novel recurrent neural network model, the predictive multiple spatio-temporal scales RNN (P-MSTRNN), which can generate as well as recognize dynamic visual patterns in the predictive coding framework. The model is characterized by multiple spatio-temporal scales imposed on neural unit dynamics through which an adequate spatio-temporal hierarchy develops via learning from exemplars. The model was evaluated by conducting an experiment of learning a set of whole body human movement patterns which was generated by following a hierarchically defined movement syntax. The analysis of the trained model clarifies what types of spatio-temporal hierarchy develop in dynamic neural activity as well as how robust generation and recognition of movement patterns can be achieved by using the error minimization principle.

Jungsik Hwang, Minju Jung, Naveen Madapana et al.

The current study examines how adequate coordination among different cognitive processes including visual recognition, attention switching, action preparation and generation can be developed via learning of robots by introducing a novel model, the Visuo-Motor Deep Dynamic Neural Network (VMDNN). The proposed model is built on coupling of a dynamic vision network, a motor generation network, and a higher level network allocated on top of these two. The simulation experiments using the iCub simulator were conducted for cognitive tasks including visual object manipulation responding to human gestures. The results showed that synergetic coordination can be developed via iterative learning through the whole network when spatio-temporal hierarchy and temporal one can be self-organized in the visual pathway and in the motor pathway, respectively, such that the higher level can manipulate them with abstraction.