Searcharxiv⌕ Search

arXiv subjects

Zhirong Su

Publications and source records attributed to Zhirong Su.

6 recordsLinked to original sources

Encoding, Decodability, and Use: A Five-Layer Framework for Benchmark Measurement Audits with Evidence from UAV Intent Recognition

Benchmark accuracy is routinely read as evidence that a model understands the construct the benchmark measures. We propose and instantiate on AeroIntent a five-layer framework that decomposes that reading into observation, representation, decoding, use, and behaviour. The framework separates encoding, decodability, and use as distinct levels. In the instantiation, the observation layer is unreliable on 7 of the 20 Drone programs and floors the direct visual correlate of radial velocity at a 0.26\% scale change. The representation layer exposes two task-designed RGB features with nominal signals. RAFT flow radial bias reaches $r=+0.257$ ($p=0.030$), and bounding-box optical-flow divergence reaches $r=+0.203$ ($p=0.029$). No multi-feature readout gives a fold-mean test correlation above the cluster minimum detectable effect (MDE), and the largest positive global out-of-sample correlation is $r=+0.080$. The decoding layer sets the MDE at $|r|=0.599$ at the multi-feature Bonferroni threshold ($α=0.00714$, power 0.80), and the observed $r=+0.080$ has power 0.00. Two injection experiments establish the MDE's condition from both sides: aligned injections are detected at or above the simulated power, and orthogonal injections are not detected. The use layer finds accuracy consistent with program memory (program-identity 0.937/0.597/0.210) and multi-region static cues. The behaviour layer is consistent with accuracy not requiring a radial-velocity readout (appearance 0.6552 vs bounding-box trajectory 0.4080, cluster-level paired $Δ=+0.2471$, $p=0.0132$).

cs.LG↗

Correctness Metric Matters: NWD-Based Calibration Loss for Tiny Person Detection in UAV Infrared Imagery

Detection calibration aligns predicted confidence with empirical correctness. Existing calibration losses inherit their correctness definition from box regression, specifically IoU against a hard threshold. We show that this target is geometrically ill-posed for tiny objects in UAV infrared imagery, where persons occupy less than 0.1\% of the image. The same pixel error is penalized more heavily as the target shrinks, so binary prediction calibration (BPC) actively suppresses confidences that should be high. On HIT-UAV, BPC with an IoU target degrades image-level localization-aware ECE (LaECE) from 0.0689 to 0.0761, 0.0649 to 0.0733, and 0.0653 to 0.0682 across Low, Mid, and High signal-to-clutter ratio (SCR) groups. We replace the IoU target with a continuous, scale-invariant normalized Wasserstein distance (NWD). The NWD target reduces LaECE\(_{\mathrm{NWD}}\) relative to BPC+IoU on all three groups (\(p<10^{-7}\)) with mAP neutral (0.9356 vs.\ 0.9347), and an independent center-offset anchor confirms that the gain is a genuine geometric correction. The improvement holds across a broad plateau of calibration weights. The NWD formulation requires no inference-time mapping layer. If a validation-fitted isotonic map is applied on top of it, calibration is lowered further, and the two corrections act on different components of the same error. The metric-level remedy has a measurable boundary. Target-background thermal pairing in the training distribution and detection-level aggregation under per-image detection-count heterogeneity lie outside it. Both are quantified independently of the NWD target.

cs.CV↗

The Paired Thermal Channel Is Two Orthogonal Axes: A Controlled Attribution Study of Calibration Cost and Detection Gain in Infrared Person Detection

The calibrated thermal channel in infrared person detection comprises two structurally orthogonal axes. True calibrated $ΔT$ outperforms scale-matched grayscale pseudo-$ΔT$ by $+0.0221$ mAP (paired Wilcoxon $p=0.0098$, Cohen's $d=+1.08$), confirming that the calibrated channel carries information the grayscale channel lacks. The calibration axis is driven by the joint pairing-scale condition. Preserving both paired correspondence and absolute calibrated scale raises expected calibration error (ECE) from $\approx 0.05$ to $0.142$. The $2\times 2$ interaction ($p=0.0059$) localizes the rise to this condition. Breaking either factor alone returns ECE to the broken-factor level (true-vs-const $p=0.002$; true-vs-shuffled $p=0.002$). Under post-hoc temperature scaling, the pairing cost survives recalibration ($p=0.002$), while the scale cost is largely absorbed ($p=0.16$). As regards the detection axis, the gain stems from structural de-structuring. Phase randomization, which destroys spatial structure while preserving per-sample variance, yields $+0.0185$ mAP over true $ΔT$ on FLIR ADAS ($p=0.014$, $d=+0.96$). The FLAME~3 gain is $+0.0064$ mAP ($p=0.078$, n=8). On the calibration axis, the same intervention is insignificant on FLIR ADAS ($p=0.47$) but significant on FLAME~3 ($p=0.0078$). These findings rest on a five-arm controlled attribution with temperature-evidential learning (TEL) as the testbed. TEL obtains a single evidence-derived routing scalar together with a complementary diagnostic entropy, and establishes a finite-evidence degeneracy theorem proving that the acquisition product degenerates to this scalar with a closed-form bound. A physical $0.5^\circ$C threshold admits cross-dataset physical readings, whereas a gray threshold of $20$ inverts without physical interpretation.

cs.CV↗

Secure Beamforming for ISAC Systems Under Communication Eavesdropper and Sensing Eavesdropper

Due to great efficiency improvement in resource and hardware space, integrated sensing and communication (ISAC) has gained much attention. In the paper, the physical layer security (PLS) of ISAC system under communication eavesdropper together with sensing eavesdropper is investigated. The system secrecy rate is maximized by transmit beamforming design of communication and sensing signals when taking sensing security, sensing performance and transmit power constraint into consideration. To deal with the formulated non-convex optimization problem, the successive convex approximation (SCA) together with the first-order Taylor expansion and semidefinite relaxation (SDR) is utilized. Additionally, it is theoretically validated that the SDR does not yield sub-optimality in the paper. Thereafter, an iterated joint secure beamforming algorithm against communication and sensing eavesdroppers is proposed. Simulation results validate the effectiveness and advance of the proposed scheme.

cs.IT↗

Generalize Hilbert operator acting on Dirichlet spaces

Let $μ$ be a positive Borel measure on the interval $[0,1)$. For $γ>0$, the Hankel matrix $\mathcal{H}_{μ,γ}=(μ_{n,k})_{n,k\geq0}$ with entries $μ_{n,k}=μ_{n+k}$, where $μ_{n+k}=\int_{0}^{\infty}t^{n+k}dμ(t)$. formally induces the operator $$\mathcal{H}_{μ,γ}=\sum_{n=0}^{\infty}\left(\sum_{k=0}^{\infty}μ_{n,k}a_k\right)\frac{Γ(n+γ)}{n!Γ(γ)}z^n,$$ on the space of all analytic functions $f(z)=\sum_{k=0}^{\infty}{a_k}{z^k}$ in the unit disc $\mathbb{D}$. Following ideas from \cite{author3} and \cite{author4}, in this paper, for $0\leqα<2$, $2\leqβ<4$, $γ\geq1$. we characterize the measure $μ$ for which $\mathcal{H}_{μ,γ}$ is bounded(resp.,compact)from $\mathcal{D}_α$ into $\mathcal{D}_β$.

math.CV↗

The range of Hilbert operator and Derivative-Hilbert operator acting on $H^1$

Let $μ$ be a positive Borel measure on the interval $[0,1)$. The Hankel matrix $\mathcal{H}_μ=(μ_{n,k})_{n,k\geq0}$ with entries $μ_{n,k}=μ_{n+k}$, where $μ_n=\int_{[0,1)}t^{n}dμ(t)$. For $f(z)=\sum_{n=0}^{\infty}a_nz^n$ is an analytic function in $\mathbb{D}$, the Hilbert operator is defined by $$\mathcal{H}_μ(f)(z)=\sum_{n=0}^{\infty}\Bigg(\sum_{k=0}^{\infty}μ_{n,k}a_k\Bigg)z^n, \quad z\in \mathbb{D}.$$ The Derivative-Hilbert operator is defined as $$\mathcal{DH}_μ(f)(z)=\sum_{n=0}^{\infty}\Bigg(\sum_{k=0}^{\infty}μ_{n,k}a_k\Bigg)(n+1)z^n, \quad z\in \mathbb{D}.$$ In this paper, we determine the range of the Hilbert operator and Derivative-Hilbert operator acting on $H^{\infty}$.

math.CV↗